+
+
+
+
+
Out[15]:
+
+
+
+
(0.7880605510627579, 0.006774486564715021)
@@ -3283,7 +3480,7 @@ tam[["pu", "peou", "itu"]]
diff --git a/surveys/surveys/surveys.ipynb b/surveys/surveys/surveys.ipynb
index f9133aa..17bd06a 100644
--- a/surveys/surveys/surveys.ipynb
+++ b/surveys/surveys/surveys.ipynb
@@ -553,6 +553,13 @@
"execution_count": 4,
"metadata": {},
"outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "0.5157738095238095\n"
+ ]
+ },
{
"data": {
"text/plain": [
@@ -586,6 +593,8 @@
"\n",
"X = [x for x, y in best_practice_score_se]\n",
"Y = [y for x, y in best_practice_score_se]\n",
+ "\n",
+ "print(sum(Y) / len(Y))\n",
"sc = plt.scatter(X, Y, c=\"black\", s=[x * 50 for x, y in best_practice_score_ds])\n",
"plt.ylabel(\"Ratio of implemented deployment best practices\")\n",
"plt.xlabel(\"Years of professional software engineering experience\")\n",
@@ -1136,7 +1145,10 @@
{
"data": {
"text/plain": [
- "(0.5515422017785757, 0.09838124227663879)"
+ "pu 6.125\n",
+ "peou 5.450\n",
+ "itu 5.950\n",
+ "dtype: float64"
]
},
"execution_count": 10,
@@ -1145,7 +1157,7 @@
}
],
"source": [
- "stats.pearsonr(tam[\"peou\"], tam[\"pu\"])"
+ "tam[[\"pu\", \"peou\", \"itu\"]].mean()"
]
},
{
@@ -1156,7 +1168,10 @@
{
"data": {
"text/plain": [
- "(0.8066270322592023, 0.004809023073123024)"
+ "pu 6.375\n",
+ "peou 5.750\n",
+ "itu 6.250\n",
+ "dtype: float64"
]
},
"execution_count": 11,
@@ -1165,7 +1180,7 @@
}
],
"source": [
- "stats.pearsonr(tam[\"peou\"], tam[\"itu\"])"
+ "tam[[\"pu\", \"peou\", \"itu\"]].median()"
]
},
{
@@ -1176,7 +1191,10 @@
{
"data": {
"text/plain": [
- "(0.7880605510627579, 0.006774486564715021)"
+ "pu 0.859990\n",
+ "peou 1.039498\n",
+ "itu 1.321825\n",
+ "dtype: float64"
]
},
"execution_count": 12,
@@ -1184,6 +1202,66 @@
"output_type": "execute_result"
}
],
+ "source": [
+ "tam[[\"pu\", \"peou\", \"itu\"]].std()"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 13,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "(0.5515422017785757, 0.09838124227663879)"
+ ]
+ },
+ "execution_count": 13,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "stats.pearsonr(tam[\"peou\"], tam[\"pu\"])"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 14,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "(0.8066270322592023, 0.004809023073123024)"
+ ]
+ },
+ "execution_count": 14,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "stats.pearsonr(tam[\"peou\"], tam[\"itu\"])"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 15,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "(0.7880605510627579, 0.006774486564715021)"
+ ]
+ },
+ "execution_count": 15,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
"source": [
"stats.pearsonr(tam[\"pu\"], tam[\"itu\"])"
]
diff --git a/thesis/chapters/0_abstract.tex b/thesis/chapters/0_abstract.tex
index e3d3ecf..7e05a31 100644
--- a/thesis/chapters/0_abstract.tex
+++ b/thesis/chapters/0_abstract.tex
@@ -1,14 +1,18 @@
\begin{abstract}
\absdiv{Background}
-Despite its long-standing history, artificial intelligence (AI) has only recently started enjoying widespread industry awareness and adoption, partly thanks to the prevalence of frameworks accessibly exposing state-of-the-art models. In order to achieve robust production deployments, the successful integration of AI components demands strong engineering methods. Concerningly, a tendency seems to be unfolding: even though professionals already have access to frameworks for deploying AI correctly, case studies and developer surveys have found that many deployments do not follow best practices.
+Despite its long-standing history, artificial intelligence (AI) has only recently started enjoying widespread industry awareness and adoption, partly thanks to the prevalence of frameworks that accessibly expose state-of-the-art models. However, the transition from prototypes to production-ready AI services is still a source of struggle across the industry. Even though professionals already have access to frameworks for deploying AI correctly, case studies and developer surveys have found that many deployments do not follow best practices.
+
\absdiv{Objective}
-This thesis investigates the reasons behind the asymmetry between the adoption of accessible AI libraries and existing reusable solutions to robust deployments. A software framework called \textit{GreatAI} is designed which aims to facilitate \underline{G}eneral \underline{R}obust \underline{E}nd-to-end \underline{A}utomated \underline{T}rustworthy AI deployments while attempting to overcome the practical drawbacks of its predecessors.
+This thesis investigates the causes of and a possible resolution to the asymmetry between the adoption of accessible AI-libraries and reusable frameworks for AI deployments. The potential solution is validated through designing a library, called \textit{GreatAI}, which aims to facilitate \underline{G}eneral \underline{R}obust \underline{E}nd-to-end \underline{A}utomated \underline{T}rustworthy deployments while attempting to overcome the practical drawbacks of its predecessors.
+
\absdiv{Method}
-The utility of \textit{GreatAI} is validated by applying the principles of design science methodology through iteratively designing it in a case study of a commercial text mining pipeline. Subsequently, interviews are conducted with practitioners to validate the generalisability of the design.
+The utility of \textit{GreatAI}'s design is validated by applying the principles of design science methodology through iteratively shaping it in a case study of a commercial text mining pipeline. Subsequently, interviews are conducted with ten practitioners for assessing its generalisability.
+
\absdiv{Results}
-To do.
+\textit{GreatAI} successfully helps implement 33 best practices through an accessible interface. These target the transition between the prototype and production phases of the AI development lifecycle. The feedback from professional data scientists and software engineers showed that ease of use and functionality are equally important in deciding to adopt deployment technologies and the proposed library was rated overwhelmingly positively in both dimensions.
+
\absdiv{Conclusions}
-To do.
+Increasing the overall maturity of industrial AI deployments by devising APIs with ease of adoption in mind is proved to be feasible. Additionally, the created software framework was deemed effective and a candidate for showcasing the utility of following best practices.
\end{abstract}
diff --git a/thesis/chapters/1_introduction.tex b/thesis/chapters/1_introduction.tex
index bbc50c0..494e822 100644
--- a/thesis/chapters/1_introduction.tex
+++ b/thesis/chapters/1_introduction.tex
@@ -2,9 +2,9 @@
Artificial intelligence techniques have recently started enjoying widespread industry awareness and adoption; the use of AI is increasingly prevalent in all sectors \cite{wirtz2019artificial,bosch2021engineering}. The reasons behind this are manifold \cite{jordan2015machine}, to name a few: recent breakthroughs in deep learning (DL), increased public awareness, an abundance of available data, access to powerful low-cost commodity hardware, education, but most interestingly, the rise of high-level libraries making ready-to-use state-of-the-art (SOTA) models easily available. The latter practically abolishes the barrier of entry for applying AI --- and with that --- can help use cases in various areas.
-However, the successful integration of AI components into production-ready applications demands strong engineering methods in order to achieve robust deployments \cite{serban2020adoption}. That is why it is as vital as ever to also focus on the quality and robustness of deployed models and software. For instance, the lack of a proper overview of data transformation steps may lead to suboptimal performance and to introducing unintended biases, which might contribute to the ever-increasing negative externality of misused AI \cite{o2016weapons}.
+However, in order to achieve robust deployments, the successful integration of AI components into production-ready applications demands strong engineering methods \cite{serban2020adoption}. That is why it is as vital as ever to also focus on the quality and robustness of deployed models and software. For instance, the lack of a proper overview of data transformation steps may lead to suboptimal performance and to introducing unintended biases, which might contribute to the ever-increasing negative externality of misused AI \cite{o2016weapons}.
-Concerningly, a peculiar tendency seems to be unfolding: even though industry professionals already have access to numerous frameworks for deploying AI correctly and responsibly, case studies and developer surveys have found that a considerable fraction of deployments does not follow best practices \cite{serban2020adoption,haakman2021ai,amershi2019software,de2019understanding,sculley2015hidden}. Utilising state-of-the-art machine learning (ML) models has become reasonably simple; applying them correctly is as difficult and nuanced as ever.
+Concerningly, a peculiar tendency seems to be unfolding: even though industry professionals already have access to numerous frameworks for deploying AI correctly and responsibly, case studies and developer surveys have found that a considerable fraction of deployments does not follow best practices \cite{serban2020adoption,haakman2021ai,amershi2019software,de2019understanding,sculley2015hidden}. Utilising state-of-the-art machine learning (ML) models has become reasonably simple; applying them correctly is as intricate and nuanced as ever.
This thesis sets out to investigate the reasons behind the apparent asymmetry between industry adoption of accessible AI-libraries and existing reusable solutions for robust AI deployments. It is hypothesised that the primary reason for the underwhelming adoption rate of best practices is the short supply of professionals equally proficient in the domains of both data science and software engineering. Nevertheless, even without their presence, practitioners could rely on frameworks for automated mature deployment processes. However, the barrier of entry for using such existing libraries is too high, especially when compared with the simplicity of AI-libraries.
@@ -25,7 +25,7 @@ I hypothesise that facilitating the adoption of AI deployment best practices is
In this case, complexity refers to the difficulty faced by professionals (Data Scientists and Software Engineers alike) when integrating third-party libraries with their solutions. This could also be described as the barrier of entry or steepness of the learning curve. If the aforementioned hypothesis is correct, the adoption of best practices can be efficiently increased by decreasing this complexity. AI deployment best practices entail the technical steps that ought to be taken to achieve robust, end-to-end, automated, and trustworthy deployments. These are detailed in Section \ref{section:requirements}.
-The existence question regarding the problem itself (\textbf{RQ1}) is answered by reviewing the literature of more than 30 published case studies in Chapter \ref{chapter:background}. \textbf{RQ2} and \textbf{RQ3} are closely connected, the design and evaluation phases utilised to answer them follow an iterative process. They are examined in Chapters \ref{chapter:design} and \ref{chapter:case} respectively. The final evaluation step is to ascertain the capability of the framework's design to generalise beyond a single subdomain and problem context. This question, \textbf{RQ4}, is investigated through interviews with industry professionals in Chapter \ref{section:interviews}.
+The existence question regarding the problem itself (\textbf{RQ1}) is answered by reviewing the literature of more than 30 published case studies in Chapter \ref{chapter:background}. \textbf{RQ2} and \textbf{RQ3} are closely connected: the design and evaluation phases utilised to answer them follow an iterative process. They are examined in Chapters \ref{chapter:design} and \ref{chapter:case} respectively. The final evaluation step is to ascertain the capability of the framework's design to generalise beyond a single subdomain and problem context. This question, \textbf{RQ4}, is investigated through interviews with industry professionals in Chapter \ref{chapter:interviews}.
\section{Structure}
diff --git a/thesis/chapters/2_background.tex b/thesis/chapters/2_background.tex
index 1fa187b..b2b37c1 100644
--- a/thesis/chapters/2_background.tex
+++ b/thesis/chapters/2_background.tex
@@ -14,7 +14,7 @@ It is not just these two packages, the list of readily available tools is vast:
In contrast to this trend, the software landscape around packaging, deploying, and maintaining machine learning (ML) --- and in general --- data-heavy applications paints a different picture. Fortunately, the related issues and their ramifications have already been thoroughly investigated.
-When looking at AI/ML\footnote{The terms AI and ML are often not differentiated and are used as synonyms in practice, for instance, see this study by the FDA \cite{food2019proposed}. ML is a well-defined subdomain of AI; however, most modern AI applications are also ML applications. Hence, conflating the two terms may be slightly imprecise but usually not wrong.} code in practice through the lens of technical debt, Sculley et al. \cite{sculley2015hidden} emphasise the repercussions of writing \textit{glue code} between the algorithms and different systems or libraries and define it as an anti-pattern. The consequence of this is the advice against using generic libraries because their rigid APIs may inhibit improvements, cause lock-in, and result in large amounts of glue code. This is a recurring theme in discussions with industry professionals.
+When looking at AI/ML\footnote{The terms AI and ML are often not differentiated and are used as synonyms in practice, for instance, see this study by the FDA \cite{food2019proposed}. ML is a well-defined subdomain of AI. However, most modern AI applications are also ML applications, hence, conflating the two terms may be slightly imprecise but usually not wrong.} code in practice through the lens of technical debt, Sculley et al. \cite{sculley2015hidden} emphasise the repercussions of writing \textit{glue code} between the algorithms and different systems or libraries and define it as an anti-pattern. The consequence of this is the advice against using generic libraries because their rigid APIs may inhibit improvements, cause lock-in, and result in large amounts of glue code. This is a recurring theme in discussions with industry professionals.
Haakman et al. \cite{haakman2021ai} interviewed 17 people at ING, which is a well-known fintech company undergoing a digital transformation to embrace AI. They found that the existing tools for ML do not meet the particularities of the field. For instance, a Feature Engineer working in the Data \& Analytics department explained that regular spreadsheets are preferred over existing solutions like MLFlow for keeping track of experiment results. The reason behind this is simplicity. Additionally, multiple other interviewees described the need to self-develop (or highly-customise) dashboards for monitoring deployed models, resulting in many non-reusable solutions across the company for the same problem. The authors conclude that there is a research gap between the ever-improving SOTA techniques and the challenges of developing real-world ML systems. In short, additional tool support is needed for facilitating the ML lifecycle.
diff --git a/thesis/chapters/3_methods.tex b/thesis/chapters/3_methods.tex
index b2b4b3f..3418016 100644
--- a/thesis/chapters/3_methods.tex
+++ b/thesis/chapters/3_methods.tex
@@ -14,7 +14,7 @@ in order to decrease the negative externality of misused AI.}
The problem context is the difficulty in responsibly transitioning (while following best practices) from prototype industrial AI applications to production-ready deployments. With the possible treatment being libraries with high-level APIs and a set of default settings. It is important to note that \textit{GreatAI} is merely a proof-of-concept, and its aim is to serve as a proxy for the design decisions behind it. Through this, the design can be indirectly evaluated. Hopefully, a by-product will be a library that can be effectively applied to this problem context.
-The practical cases used for the evaluation are further elaborated in Chapter \ref{chapter:case}. In short, they focus on individual components of a growing commercial platform with the aim of finding tech-transfer opportunities in academic publications. The primary inputs of the system as a whole are PDF files, while the output is a list of metrics describing various aspects of each paper, such as interesting sentences, scientific domains, and contributions. The result also includes a predicted score used for ranking. This ranking is subsequently processed by the business developers of Technology Transfer Offices (TTOs) of multiple Dutch and German universities, who later give feedback on the results.
+The practical cases used for the evaluation are further elaborated in Chapter \ref{chapter:case}. In short, they focus on individual components of a growing commercial platform which aims to find tech-transfer opportunities in academic publications. The primary input of the system as a whole is PDF files, while the output is a list of metrics describing various aspects of each paper, such as interesting sentences, scientific domains, and contributions. The result also includes a predicted score used for ranking. This ranking is subsequently processed by the business developers of Technology Transfer Offices (TTOs) of multiple Dutch and German universities, who later give feedback on the results.
Overall, this problem context carries the properties of typical industry use-cases: it utilises a wide range of natural language processing methods, contains complex interactions between the services, benefits from the integration of end-to-end feedback, and has to provide the clients with a platform that they can rely on in their organisation's core processes. Since the final ranking affects real people, explainability and robustness are also central questions.
@@ -24,7 +24,7 @@ Before generalising, the framework's design is iteratively refined using the fee
To conclusively answer \textbf{RQ3} and \textbf{RQ4}, interviews are conducted with a population of software engineers and data scientists with varying levels of professional background. Since my colleagues and I are likely to have a bias for (or against) the proposed design, the first step of checking its applicability in other practical contexts is to ask the opinion of non-affiliated practitioners.
-First, before their interview, interviewees are requested to complete a questionnaire (shown in Appendix \ref{appendix:practices}) about their last completed AI project; the questions refer to the best practices implemented by \textit{GreatAI} as described in Tables \ref{table:best-practices-1} and \ref{table:best-practices-2}. They are also advised to take a quick look at the tutorial page of the documentation. The interviews are divided into two halves. In the first part, after a brief introduction, participants are asked to solve a real-world task by finishing a partially completed example application using \textit{GreatAI}. They are also encouraged to think aloud so their feedback can be noted. Successfully completing the task creates a system implementing a known number of best practices. This way, the added value --- in terms of a larger number of implemented best practices --- can be quantitatively analysed by comparing the qualities of the finished implementation with the previously given answers.
+First, before their interview, paricipants are requested to complete a questionnaire (shown in Appendix \ref{appendix:practices}) about their last completed AI project; the questions refer to the best practices implemented by \textit{GreatAI}. They are also advised to take a quick look at the tutorial page of the documentation. The interviews are divided into two halves. In the first part, after a brief introduction, interviewees are asked to solve a real-world task by finishing a partially completed example application using \textit{GreatAI}. They are also encouraged to think aloud so their feedback can be noted. Successfully completing the task creates a system implementing a known number of best practices. This way, the added value --- in terms of a larger number of implemented best practices --- can be quantitatively analysed by comparing the qualities of the finished implementation with the previously given answers.
Notes are taken throughout the interviews and subsequently extended using reflective journaling \cite{halcomb2006verbatim} combined with thematic coding. After which, the insights from the interviewed professionals are distilled using the techniques of thematic analysis \cite{fereday2006demonstrating} following the methodologies of \cite{cruz2019catalog} and \cite{haakman2021ai}. These insights can then be combined with the numerical results to explain and elaborate on them.
diff --git a/thesis/chapters/4_design.tex b/thesis/chapters/4_design.tex
index 8c59818..5f94bc5 100644
--- a/thesis/chapters/4_design.tex
+++ b/thesis/chapters/4_design.tex
@@ -6,7 +6,7 @@ Providing users with a high level of abstraction is not unheard of in the domain
As highlighted by several case studies in Chapter \ref{chapter:background}, the transition from prototypes to production-ready systems is often named as the source of unexpected struggle. Maybe it is not a coincidence that a significant portion of the SE4ML best practices should be implemented in this phase. Unfortunately, it is easy to gloss over them while tackling the underestimated difficulties of this \textit{transition}. Therefore, the aim of \textit{GreatAI} is to ease this step of the lifecycle. Consequently, its scope is limited to the \textit{transition} step.
-There have been attempts that at least partially address this issue, however, as we have seen in Chapter \ref{chapter:background}, these have limitations either from the perspective of best practices or stemming from their difficulty in being adopted. To have the best chance of providing an easy-to-adopt solution, the scope has to be well-defined and limited. To understand the API of a library, users first need to understand its aim, surface, and have to become familiar with the problems it solves. Thus, focusing only on the \textit{transition} step seems reasonable. This step is highlighted in Figure \ref{fig:scope}.
+There have been attempts that at least partially address this issue; however, as we have seen in Chapter \ref{chapter:background}, these have limitations either from the perspective of best practices or stemming from their difficulty in being adopted. The scope has to be well-defined and limited to provide the best chance of providing an easy-to-adopt solution. To understand the API of a library, users first need to understand its aim and surface, and have to become familiar with the problems it solves. Thus, focusing only on the \textit{transition} step seems reasonable. This step is highlighted in Figure \ref{fig:scope}.
\begin{figure}
\centering
@@ -16,21 +16,21 @@ There have been attempts that at least partially address this issue, however, as
\label{fig:scope}
\end{figure}
-It is interesting to mention that \href{https://xkcd.com/927/}{there is a proliferation} of platform/software as a service (PaaS/SaaS) products for deploying AI\footnote{Such as \href{https://mlem.ai/}{MLEM}, \href{https://streamlit.io/cloud}{Streamlit} or any AutoML SaaS platform, for example, \href{https://www.akkio.com/role/software-engineers}{Akkio} as these often have a one-click deployment feature as well.}. At first, these may look intriguing. However, they tend to only focus on getting code easily deployed in the cloud: AI best practices are not prioritised in this setup. Nevertheless, in many cases, it may be a suitable option to use such a service, and these can also complement \textit{GreatAI} as illustrated in Figure \ref{fig:scope}: first, the prototype is transformed into a GREAT service and materialised as a common software artifact implementing the best practices. Then, it is either deployed using a deployment SaaS or by using the organisation's existing software deployment setup.
+It is interesting to mention that \href{https://xkcd.com/927/}{there is a proliferation} of platform/software as a service (PaaS/SaaS) products for deploying AI\footnote{Such as \href{https://mlem.ai/}{MLEM}, \href{https://streamlit.io/cloud}{Streamlit} or any AutoML SaaS platform, for example, \href{https://www.akkio.com/role/software-engineers}{Akkio} as these often have a one-click deployment feature as well.}. At first, these may look intriguing. However, they tend to only focus on getting code easily deployed in the cloud: AI best practices are not prioritised in this setup. Nevertheless, in many cases, it may be a suitable option to use such a service, and these can also complement \textit{GreatAI} as illustrated in Figure \ref{fig:scope}: first, the prototype is transformed into a \textit{GREAT} service and materialised as a common software artifact implementing the best practices. Then, it is either deployed using a deployment SaaS or by using the organisation's existing software deployment setup.
\section{Requirements} \label{section:requirements}
The best practices (which are referenced throughout the thesis) with which the design is concerned are a subset of those compiled by Serban et al. \cite{serban2020adoption,serban2021practices} and John et al. \cite{john2020architecting}. The core requirements --- set of covered best practices --- for a software solution that has the potential to improve our problem context are presented in the following, along with some explanation and clarification for each of them.
-\paragraph{General} Albeit not explicitly in the list of best practices, compatibility is vital in encouraging adoption. Large projects oftentimes end up depending on numerous packages, each of which may impose some restrictions on the code: since these all have to be satisfied simultaneously, this can result in severe constraints.
+\paragraph{General} Albeit not explicitly in the list of best practices, compatibility is vital in encouraging adoption. Large projects frequently end up depending on numerous packages, each of which may impose some restrictions on the code: since these all have to be satisfied simultaneously, this can result in severe constraints.
The open-source scene of data-related libraries is vibrant. To take the example of data validation, there are at least 4 popular choices which offer varying but similar features: \href{https://github.com/SeldonIO/alibi-detect}{Alibi detect}, \href{https://github.com/PAIR-code/facets}{Facets}, \href{https://github.com/great-expectations/great_expectations}{Great Expectations}, and Data Linter \cite{hynes2017data}. The responsibility of choosing the most fitting solution falls on the user. Thus, they should not be limited in this by \textit{GreatAI}.
-The programming language (PL) of the library should be its only non-general property. Fortunately, the de facto PL for data science is Python. Hence, implementing the library in it should not significantly limit its applicability.
+The programming language (PL) of the library should be its only non-general property. Fortunately, the de facto PL for data science is Python, so implementing the library in it should not significantly limit its applicability.
\paragraph{Robustness} in software development can be achieved by preparing the application to handle errors gracefully, even unexpected ones \cite{bishop1998robust}. Errors can and will happen in practice: storing and investigating what has led to them is required to prevent future ones. In the case of ML, errors might not be as obvious to detect as in more traditional applications (see the above-mentioned data validators). Even if a single feature's value falls outside the expected distribution, unexpected results can happen. In cases where this might lead to real-world repercussions, extra care has to be taken to construct as many safeguards as feasible. \textit{GreatAI} should support its clients in this.
-\paragraph{End-to-end} In this case, it refers to end-to-end feedback. That is, feedback should be gathered on the real-world performance of the system, and this should be taken into account when designing/training the next iteration of the model. Static datasets may fail to capture the changing nature of real life and can become outdated if they are not revised continuously. A well-packaged deployment should make it trivial to integrate new training data.
+\paragraph{End-to-end} In this case, it refers to end-to-end feedback. That is, feedback should be gathered on the system's real-world performance, which should be taken into account when designing/training the next iteration of the model. Static datasets may fail to capture the changing nature of real life and can become outdated if they are not revised continuously. A well-packaged deployment should make it trivial to integrate new training data.
\paragraph{Automated} The available time of data scientists and software engineers is limited and expensive. For this reason, humans should only be involved when their involvement is necessary. Steps in the development process that can be automated without negative consequences must be automated in order to achieve efficient development processes and let the experts focus on the issues that require their attention the most.
@@ -40,9 +40,9 @@ These requirements were chosen stemming from their general importance and potent
\section{Design principles}
-Before diving into the concrete issues solved, let us detail the principles that should be used for implementing them in the scope of this framework. As implied in Section \ref{section:scope}, the Unix philosophy \cite{ritchie1978unix,salus1994quarter} of software design is followed. Most notably, the design goal that encourages to \textit{write programs that do one thing and do it well.}\footnote{Of course, \textit{write programs to work together} is also very much applicable since allowing interoperability is one of the core requirements for \textit{GreatAI}.}. Apart from providing a clear and simple picture of the intended use-cases for the library, this is also in line with the main notion of \textit{A Philosophy of Software Design} \cite{ousterhout2018philosophy}: APIs should be narrow and deep. A narrow width refers to having a small exposed surface area, i.e. having a small number of functions and classes in the public API. While depth implies each of them accomplishing an involved, complex goal.
+Before diving into the concrete issues solved, let us detail the principles that should be used for implementing them in the scope of this framework. As implied in Section \ref{section:scope}, the Unix philosophy \cite{ritchie1978unix,salus1994quarter} of software design is followed. Most notably, the design goal that encourages to \textit{write programs that do one thing and do it well.}\footnote{Of course, \textit{write programs to work together} is also very much applicable since allowing interoperability is one of the core requirements for \textit{GreatAI}.}. Apart from providing a clear and simple picture of the intended use-cases for the library, this is also in line with the main notion of \textit{A Philosophy of Software Design} \cite{ousterhout2018philosophy}: APIs should be narrow and deep. A narrow width refers to having a small exposed surface area, i.e. having a small number of functions and classes in the public API. In contrast, depth implies that each accomplishes an involved, complex goal.
-In a way, the width of an API is the price users have to pay (the effort required for learning it) to use it, while the depth is analogous to the return they get from it. Having to learn little and being provided with a lot of functionality maximises return on investment (ROI), hence, developer experience (DX). The theoretical frameworks presented in \textit{The Programmer's Brain} \cite{hermans2021programmer} provides us with explanations and vocabulary from psychology for arguing about the cognitive aspects of API design. In the following, two of them will be used for detailing the design principles: cognitive dimensions of code bases (CDCB) which is an extension of the cognitive dimensions of notation (CDN) framework \cite{blackwell2001cognitive}, and linguistic anti-patterns \cite{arnaoudova2016linguistic}. The former comes with a set of dimensions describing different (often competing) cognitive aspects of code that influence one's ability to perform certain tasks.
+In a way, the width of an API is the price users have to pay (the effort required for learning it) to use it, while the depth is analogous to the return they get from it. Having to learn little and being provided with a lot of functionality maximises return on investment (ROI), hence, developer experience (DX). The theoretical frameworks presented in \textit{The Programmer's Brain} \cite{hermans2021programmer} provides us with explanations and vocabulary from psychology for arguing about the cognitive aspects of API design. In the following, two of them will be used for detailing the design principles: cognitive dimensions of code bases (CDCB) which is an extension of the cognitive dimensions of notation (CDN) framework \cite{blackwell2001cognitive}, and linguistic anti-patterns \cite{arnaoudova2016linguistic}. The former comes with a set of dimensions describing different (often competing) cognitive aspects of code that influence one's ability to perform specific tasks.
Linguistic anti-patterns provide guidelines for improving consistency and decreasing the false sense of consistency when there is none. Also, choosing the right names for identifiers can help activate information stored in the long-term memory, making it quicker to comprehend and easier to reason about the code \cite{deissenboeck2006concise}. Finding the most accurate and useful names is more challenging than it first seems. Accuracy and usefulness are already often competing goals. The more precise the name, the longer and therefore less convenient to use \cite{butler2009relating}. In short, good names are essential to good APIs; consciously considering the implications of names should be an integral part of the design process.
@@ -56,15 +56,15 @@ For example, tracing the evaluations and the model versions used in a distribute
Being \textit{automated} is listed as a requirement, but it is imperative to only automate for simplifying and not for hiding decisions. More precisely, guessing must not be a part of automation. For instance --- an otherwise handy WebGL library --- TWGL.js, has a feature for automatically guessing the type of vectors based on their names. Suppose it matches the \texttt{/colou?r/i} pattern. In that case, it is treated as a vector with three components\footnote{\href{https://github.com/greggman/twgl.js/blob/e3a8d0ed09f7f5cd4be0e4cb5976081c2b5013aa/src/attributes.js\#L139}{\tiny github.com/greggman/twgl.js/blob/e3a8d0ed09f7f5cd4be0e4cb5976081c2b5013aa/src/attributes.js\#L139}}. It is easy to imagine that this can help in certain scenarios. Still, it does so at the cost of immense confusion when correctly renaming a variable breaks the application. In CDCB, this equates to scoring high on the dimension of \textit{Hidden dependencies} and low on \textit{Visibility}.
-Learning from this, any kind of guessing must be avoided to create a pleasant API. However, this conflicts with providing defaults for each configuration value. Even if these would be reasonable defaults derived from educated guesses, they are still merely guesses. Nevertheless, if the users were required to specify each configuration option, that would lead to considerably more boilerplate code. This verbosity is captured by the \textit{Diffuseness} dimension of CDCB and, of course, should be minimised.
+Learning from this, any guessing must be avoided to create a pleasant API. However, this conflicts with providing defaults for each configuration value. Even if these would be reasonable defaults derived from educated guesses, they are still merely guesses. Nevertheless, if the users were required to specify each configuration option, that would lead to considerably more boilerplate code. This verbosity is captured by the \textit{Diffuseness} dimension of CDCB and, of course, should be minimised.
-To resolve this conflict, \textit{GreatAI} should have recommended values instead of defaults. This can mean a context object (as suggested in \cite{ousterhout2018philosophy}), which contains the result of each design consideration that has to be made for a service's deployment. If not configured manually, the recommended values are applied automatically, just like defaults. The values chosen for each parameter must be clearly highlighted. Coming from the library's single responsibility, the number of parameters should not be immense; hence, the user can be expected to comprehend them instead of just being overwhelmed and skimming it.
+To resolve this conflict, \textit{GreatAI} should have recommended values instead of defaults. This can mean a context object (as suggested in \cite{ousterhout2018philosophy}), which contains the result of each design consideration that has to be made for a service's deployment. If not configured manually, the recommended values are applied automatically, just like defaults. The values chosen for each parameter must be clearly highlighted. Coming from the library's single responsibility, the number of parameters should not be immense; hence, the user can be expected to comprehend them instead of just being overwhelmed and skipping them.
This way, the library attempts to notify its user about the existence of these decisions but does not force them to decide manually. As a result, no initial configuration is needed for starting out with the library (high \textit{Provisionality}, low \textit{Diffuseness}), and the dependencies are not hidden since they are explicitly highlighted.
\subsection{Documentation}
-Little value can be derived from software without good documentation; undoubtedly, good documentation is a prerequisite for adoption. Documentation comes in many shapes: modern integrated development environments (IDEs) tend to show a popup of a function's description when requested (for instance, on mouse hover), and at the same time, a more comprehensive online manual and example projects are also still expected. But descriptive error messages can also be viewed as documentation.
+Little value can be derived from software without good documentation; undoubtedly, good documentation is a prerequisite for adoption. Documentation comes in many shapes: modern integrated development environments (IDEs) tend to show a popup of a function's description when requested (for instance, on mouse hover), and at the same time, a more comprehensive online manual and example projects are also still expected. Descriptive error messages can also be viewed as documentation.
The library must have quality documentation for all categories. Accordingly, for structuring it, the \textit{Diátaxis} philosophy is preferred \cite{Procida_Diataxis_documentation_framework} which prescribes dividing documentation into 4 parts along 2 axes: practical-theoretical and passive-active consumption. The four quadrants derived from this are tutorials, how-to guides, references, and explanations.
@@ -80,4 +80,4 @@ Subjectively, a key component of good DX is \textit{Progressive evaluation} thro
At the same time, Python codebases are rarely strictly object-oriented (OO). They are a mix of the functional, data-driven, and OO paradigms. Consequently, relying on classes for grouping related functions is not always desirable; therefore, it is even more imperative to name similar functions similarly. This helps discoverability and chunking \cite{hermans2021programmer}, which amounts to quicker comprehension.
-There is one more reason to prefer consistency: humans have limited short-term memory (STM) \cite{miller1956magical}. Even though flags as function parameters are frowned upon by some \cite{martin2009clean}, they are useful, especially when configuring libraries. However, if there is no convention for the default value of a flag, clients have to remember the flag's name and initial value simultaneously, quickly overloading their STM. Thus, in the codebase, all defaults must be the same, let us say, \texttt{False}. Sometimes, it can result in a \textit{disable} prefix, which may turn into a double negation. Nevertheless, users should never encounter this since the doubly-negated version is the default; thus, when overriding it, it is only singly negated. This approach also implies that something may be recommended to be turned on by default.
+There is one more reason to prefer consistency: humans have limited short-term memory (STM) \cite{miller1956magical}. Even though flags as function parameters are frowned upon by some \cite{martin2009clean}, they are useful, especially when configuring libraries. However, if there is no convention for the default value of a flag, clients have to remember the flag's name and initial value simultaneously, quickly overloading their STM. Thus, in the codebase, all defaults must be the same, let us say, \texttt{False}. Sometimes, it can result in a \textit{disable} prefix, which may turn into a double negation. Nevertheless, users should never encounter this since the doubly-negated version is the default; thus, it is only singly negated when overriding it. This approach also implies that something may be recommended to be turned on by default.
diff --git a/thesis/chapters/5_cases/main.tex b/thesis/chapters/5_cases/main.tex
index 97a770e..ae635ef 100644
--- a/thesis/chapters/5_cases/main.tex
+++ b/thesis/chapters/5_cases/main.tex
@@ -8,7 +8,7 @@ To achieve this, we have a service-based architecture \cite{kleppmann2017designi
I was among the first engineers on the team, which has grown considerably in the past two years. While architecting, designing, and integrating more and better models into our software solution, I experienced the same difficulties as were described in Chapter \ref{chapter:background}. The gap between prototypes and production-ready services is larger than it seems, and it is also larger than it should be. This has motivated me to investigate the state-of-the-art, and I have found that it is insufficient in many cases. Since the ScoutinScience platform is a typical example of applying AI in the industry, it will serve as the real-life case, problem context, and testbed for attempting to design a solution that can hopefully advance the state-of-the-art.
-In this chapter, the process of designing \textit{GreatAI} is described, along with how it fits into real-life use-cases. First, a simple experiment is presented, which leads to the implementation of a software service. Subsequently, as the feature set of the library grows and matures, a more complex component is developed. Lastly, the final version of the design is presented and qualitatively evaluated to verify how well it satisfies the requirements described in Section \ref{section:requirements}.
+This chapter describes the process of designing \textit{GreatAI} and how it fits into real-life use cases. First, a simple experiment is presented, which leads to the implementation of a software service. Subsequently, as the feature set of the library grows and matures, a more complex component is developed. Lastly, the final version of the design is presented and qualitatively evaluated to verify how well it satisfies the requirements described in Section \ref{section:requirements}.
\input{chapters/5_cases/naive-bayes}
\input{chapters/5_cases/scibert}
diff --git a/thesis/chapters/5_cases/naive-bayes.tex b/thesis/chapters/5_cases/naive-bayes.tex
index 565109f..b4ce7d7 100644
--- a/thesis/chapters/5_cases/naive-bayes.tex
+++ b/thesis/chapters/5_cases/naive-bayes.tex
@@ -1,12 +1,12 @@
\section{Domain classification with Naïve Bayes} \label{section:simple-case}
-Using different models for slight variations of the same problem is quite commonplace in the industry. For instance, UberEats has a vast, hierarchical set of models for every country, region, and city for calculating the estimated time of delivery \cite{li2017scaling}. We have also found that in order to best process an academic publication, knowing its domain is essential. The reason for this can be (among others) the wildly different vocabularies of different domains. For example, the term \textit{framework} in computer science almost always refers to a software artifact (usually implying high tech-transfer potential), while in most other domains, \textit{framework} is used to describe theoretical models that are less central to practical applications. Of course, it is not merely the meaning of the terms but more importantly: their distribution that varies significantly. Therefore, the topic of this section is to design and develop a domain prediction model for academic papers.
+Using different models for slight variations of the same problem is commonplace in the industry. For instance, UberEats has a vast, hierarchical set of models for every country, region, and city for calculating the estimated time of delivery \cite{li2017scaling}. We have also found that in order to best process an academic publication, knowing its domain is essential. The reason for this can be (among others) the wildly different vocabularies of different domains. For example, the term \textit{framework} in computer science almost always refers to a software artifact (usually implying high tech-transfer potential). In contrast, in most other domains, \textit{framework} is used to describe theoretical models that are less central to practical applications. Of course, it is not merely the meaning of the terms but, more importantly, their distribution that varies significantly. Therefore, the topic of this section is to design and develop a domain prediction model for academic papers.
\subsection{Background}
-Fortunately, this is one of the oldest text classification tasks. In fact, Maron introduced the Naïve Bayes classifier in 1961 \cite{maron1961automatic} for exactly this purpose: classifying documents' subjects. However, it is still an active problem when it comes to academic texts as indicated by Elsevier-funded research carried out by Rivest et al. \cite{rivest2021level}. They created a 176-class classification problem for comparing bibliometric and deep-learning approaches but this comparison is made difficult because 44\% of the labels are \textit{assigned suboptimally} in the ground-truth dataset.
+Fortunately, this is one of the oldest text classification tasks. In fact, Maron introduced the Naïve Bayes classifier in 1961 \cite{maron1961automatic} for precisely this purpose: classifying documents' subjects. However, it is still an active problem when it comes to academic texts, as indicated by Elsevier-funded research carried out by Rivest et al. \cite{rivest2021level}. They created a 176-class classification problem for comparing bibliometric and deep-learning approaches. However, this comparison is made difficult because 44\% of the labels are \textit{assigned suboptimally} in the ground-truth dataset.
-Prior work evaluated SciBERT \cite{beltagy2019scibert} --- a BERT \cite{devlin2018bert} model pretrained on academic publications --- on a simpler version of the task in which the domains of sentences\footnote{Sentences are more appropriate units for processing due to SciBERT's maximum token length of 512 which comes from its attention mechanism's quadratic complexity \cite{vaswani2017attention}.} have to be decided\footnote{\href{https://paperswithcode.com/sota/sentence-classification-on-paper-field}{paperswithcode.com/sota/sentence-classification-on-paper-field}}. It achieved an F1-score of $0.6571$ after being pretrained on the Semantic Scholar Corpus (SSC) \cite{Lo2020S2ORCTS} and finetuned on the train split of the Microsoft Academic Graph (MAG) dataset \cite{wang2019review}\footnote{SciBERT was applied to a preprocessed version (\href{https://github.com/allenai/scibert/tree/master/data/text_classification/mag}{github.com/allenai/scibert/tree/master/data/text\_classification/mag}) of this dataset.}. To the best of my knowledge, no other published work exists on this sentence classification task. This may be explained by the lack of practical relevance and contrived nature (uniform label distribution) of the task as we will see in the next subsection.
+Prior work evaluated SciBERT \cite{beltagy2019scibert} --- a BERT \cite{devlin2018bert} model pretrained on academic publications --- on a simpler version of the task in which the domains of sentences\footnote{Sentences are more appropriate units for processing due to SciBERT's maximum token length of 512 which comes from its attention mechanism's quadratic complexity \cite{vaswani2017attention}.} have to be decided\footnote{\href{https://paperswithcode.com/sota/sentence-classification-on-paper-field}{paperswithcode.com/sota/sentence-classification-on-paper-field}}. It achieved an F1-score of $0.6571$ after being pretrained on the Semantic Scholar Corpus (SSC) \cite{Lo2020S2ORCTS} and finetuned on the train split of the Microsoft Academic Graph (MAG) dataset \cite{wang2019review}\footnote{SciBERT was applied to a preprocessed version (\href{https://github.com/allenai/scibert/tree/master/data/text_classification/mag}{github.com/allenai/scibert/tree/master/data/text\_classification/mag}) of this dataset.}. To my knowledge, no other published work exists on this sentence classification task. This may be explained by the task's lack of practical relevance and contrived nature (uniform label distribution), as we will see in the following subsection.
\begin{displayquote}
\textbf{Design note} After getting familiar with the context, it is time to focus on experimenting and developing our domain prediction service. At the same time, the difficulties encountered should be noted and integrated into \textit{GreatAI}'s design.
@@ -14,9 +14,9 @@ Prior work evaluated SciBERT \cite{beltagy2019scibert} --- a BERT \cite{devlin20
\subsection{Data}
-Two datasets will be considered for the experiments. SciBERT's MAG and the SSC. The former is used to compare the results with SciBERT's, while the latter is utilised for training a model for production purposes because it has 19 labels compared with MAG's 7 and it also contains abstracts instead of just sentences, thus, it is more fitting for our practical use-case.
+Two datasets will be considered for the experiments. SciBERT's MAG and the SSC. The former is used to compare the results with SciBERT's, while the latter is utilised for training a model for production purposes because it has 19 labels compared with MAG's seven, and it also contains abstracts instead of just sentences; thus, it is more fitting for our practical use-case.
-SciBERT's version of the MAG dataset has 84 thousand and 22.3 thousand sentences in its train and test splits respectively. These are mostly in English and have all punctuation and casing removed. Each sentence is classified as belonging to one of seven fields. Figure \ref{fig:mag-distribtion} shows that the classes have a uniform distribution.
+SciBERT's version of the MAG dataset has 84 thousand and 22.3 thousand sentences in its train and test splits, respectively. These are mostly in English and have all punctuation and casing removed. Each sentence is classified as belonging to one of seven fields. Figure \ref{fig:mag-distribtion} shows that the classes have a uniform distribution.
\begin{figure}
\centering
@@ -26,13 +26,13 @@ SciBERT's version of the MAG dataset has 84 thousand and 22.3 thousand sentences
\label{fig:mag-distribtion}
\end{figure}
-SSC is much larger: it contains over 80 million abstracts. Having more data certainly helps in sampling the term distribution more accurately, nonetheless, the law of diminishing returns applies, especially when using simple models. Therefore, the data will be randomly downsampled to leave us with a more manageable couple of hundreds of megabytes of abstracts. We can see the distribution of class labels in Figure \ref{fig:ss-distribution}. The dataset is considerably less balanced: \textit{medicine} is by far the most voluminous field.
+SSC is much larger: it contains over 80 million abstracts. Having more data certainly helps in sampling the term distribution more accurately; nonetheless, the law of diminishing returns applies, especially when using simple models. Therefore, the data will be randomly downsampled to give us a more manageable couple of hundreds of megabytes of abstracts. We can see the distribution of class labels in Figure \ref{fig:ss-distribution}. The dataset is considerably less balanced: \textit{medicine} is by far the most voluminous field.
\begin{figure}
\centering
\includegraphics[width=0.8\linewidth]{figures/ss-distribution.png}
\captionsetup{width=.9\linewidth}
- \caption{Label distribution of the Semantic Scholar dataset \cite{Lo2020S2ORCTS}. Each publication may be assigned at most 3 domains.}
+ \caption{Label distribution of the Semantic Scholar dataset \cite{Lo2020S2ORCTS}. Each publication may be assigned at most three domains.}
\label{fig:ss-distribution}
\end{figure}
@@ -40,7 +40,7 @@ SSC is much larger: it contains over 80 million abstracts. Having more data cert
\textbf{Where should we store this data?} ``On my machine'' seems like an easy answer. However, if we have a team working with the data or it has intrinsic value, it must be stored in an easy-to-access, potentially redundant way. Serban et al. \cite{serban2020adoption} expressed this need in the following best practice: \textit{Make Data Sets Available on Shared Infrastructure (private or public)}. Meanwhile, wherever data is stored, it should also be versioned to satisfy the next best practice: \textit{Use Versioning for Data, Model, Configurations, and Training Scripts}.
\end{displayquote}
-MAG needs no further preprocessing if we aim to match SciBERT's setup \cite{beltagy2019scibert}. But since SSC contains heaps of metadata, the relevant parts have to be extracted and preprocessed. In this case, these are the concatenation of the abstract's text and the paper's title along with the paper's domains (there can be multiple domains for a single paper: it is a multi-label classification task). Lastly, the non-English entries are discarded because we only expect to process papers in English.
+MAG needs no further preprocessing if we aim to match SciBERT's setup \cite{beltagy2019scibert}. However, since SSC contains heaps of metadata, the relevant parts have to be extracted and preprocessed. In this case, these are the concatenation of the abstract's text and the paper's title along with the paper's domains (there can be multiple domains for a single paper: it is a multi-label classification task). Lastly, the non-English entries are discarded because we only expect to process papers in English.
\begin{displayquote}
\textbf{How should we preprocess the data?} These simple processing steps (filter, map, project) are almost always present in the data science lifecycle. For example, cleaning the input text from various HTML, OCR, PDF, or \LaTeX \hskip 0.12cm extraction artifacts is almost always necessary for text analysis. This is captured in the \href{https://se-ml.github.io/practices}{AI best practices collection} under the following category: \textit{Write Reusable Scripts for Data Cleaning and Merging}. Also, the best practice of \textit{Test all Feature Extraction Code} is somewhat applicable: the applied processing steps must not introduce unwanted artifacts.
@@ -50,11 +50,11 @@ MAG needs no further preprocessing if we aim to match SciBERT's setup \cite{belt
Our aims are twofold: (1) to evaluate a sentence classification model on MAG and compare it with prior art; and (2) to retrain and apply this model for classifying publication metadata (including abstracts). This would allow the ScoutinScience platform to select an appropriate processing pipeline which has been trained on a matching vocabulary (and domain) for each publication.
-It seems reasonable that only considering the distribution (frequencies) of individual terms may be sufficient. To test this hypothesis, a unigram language model (Multinomial Naïve Bayes) is constructed and its accuracy is compared with SciBERT's. The former definitely aligns with the advice to \textit{Use The Most Efficient Models}.
+It seems reasonable that only considering the distribution (frequencies) of individual terms may be sufficient. For testing this hypothesis, a unigram language model (Multinomial Naïve Bayes) is constructed, and its accuracy is compared with SciBERT's. The former definitely aligns with the advice to \textit{Use The Most Efficient Models}.
-Using the MNB implementation of scikit-learn \cite{pedregosa2011scikit}, it only took a couple of lines to create, hyperparameter-optimise, and test a text classifier. Including data loading and visualisations, it takes 71 lines of code (LOC) to be more precise. \footnote{The code is available at \href{https://great-ai.scoutinscience.com/tutorial/}{great-ai.scoutinscience.com/tutorial}.} This further proves relatively how simple it is to use standard packages. The code can be considered for satisfying the \textit{Automate Hyper-Parameter Optimisation} best practice since it also implements an automated hyperparameter sweep.
+Using the MNB implementation of scikit-learn \cite{pedregosa2011scikit}, it only took a couple of lines to create, hyperparameter-optimise, and test a text classifier. Including data loading and visualisations, it takes 71 lines of code (LOC) to be more precise. \footnote{The code is available at \href{https://great-ai.scoutinscience.com/tutorial/}{great-ai.scoutinscience.com/tutorial}.} This further proves how simple it is to use standard packages. The code can be considered for satisfying the \textit{Automate Hyper-Parameter Optimisation} best practice since it also implements an automated hyperparameter sweep.
-The sentences are tokenised into words and vectorised with TF-IDF (with logarithmic term frequency) \cite{buckley1985implementation}, the hyperparameters found via 10-fold cross-validation on the \textit{train} split lead to filtering out tokens which occur in fewer than 5 documents or more than 5\% of the documents.
+The sentences are tokenised into words and vectorised with TF-IDF (with logarithmic term frequency) \cite{buckley1985implementation}, the hyperparameters found via 10-fold cross-validation on the \textit{train} split lead to filtering out tokens which occur in fewer than five documents or more than 5\% of the documents.
\begin{displayquote}
\textbf{What could be automated here?} As discussed in Section \ref{section:accessible-ai}, libraries exposing algorithms and even SOTA models can already be considered mature and accessible. In this case, only scikit-learn was utilised, but subjectively, most popular libraries have a similarly easy-to-use API. Therefore, I see no urgent need for further action regarding the \textit{experimentation} step of the lifecycle in connection with the AI best practices.
@@ -78,27 +78,27 @@ The sentences are tokenised into words and vectorised with TF-IDF (with logarith
\label{fig:ss-confusion}
\end{figure}
-When this model is applied to the \textit{test} split of MAG, we get the confusion matrix of Figure \ref{fig:mag-confusion}. This Naïve Bayes classifier achieves a whopping $0.6795$ F1-score. This is $2.3\%$ more than SciBERT's on the same dataset. Thus, it seems, MNB clearly outperforms SciBERT for this particular use case: it is not only more accurate, its model is magnitudes smaller, while it is also considerably faster to train (or finetune in the case of SciBERT) and use (its running time is in the order of milliseconds per publication). It also has no upper limit on the input length. Thus, this experiment validates the choice of picking MNB for the task over SciBERT.
+When this model is applied to the \textit{test} split of MAG, we get the confusion matrix of Figure \ref{fig:mag-confusion}. This Naïve Bayes classifier achieves a whopping $0.6795$ F1 score. This is $2.3\%$ more than SciBERT's on the same dataset. Thus, it seems that MNB clearly outperforms SciBERT for this particular use case: it is not only more accurate, but its model is magnitudes smaller, while it is also considerably faster to train (or finetune in the case of SciBERT) and use (its running time is in the order of milliseconds per publication). It also has no upper limit on the input length. Thus, this experiment validates choosing MNB for the task over SciBERT.
-It is, of course, not entirely surprising that the sophisticated transformer architecture of SciBERT is not necessary for a plain task like this. Apart from phrases, the relation between separate words of a sentence do not carry nearly as much discriminative power as the identity of the terms \cite{hand2001idiot}, hence, there is little reason for using an attention mechanism. The fact that SciBERT even works in any way on this task is already a testament to its general applicability. Nevertheless, this short experiment has proved that we can safely opt for using MNB for production.
+It is, of course, not entirely surprising that the sophisticated transformer architecture of SciBERT is not necessary for a straightforward task like this. Apart from phrases, the relations between separate words of a sentence do not carry nearly as much discriminative power as the identity of the terms \cite{hand2001idiot}; hence, there is little reason for using an attention mechanism. The fact that SciBERT even works in any way on this task is already a testament to its general applicability. Nevertheless, this short experiment has proved that we can safely opt for using MNB for production.
-Since Multinomial Naïve Bayes is best at returning a single label and SSC has multiple labels per datapoint: for evaluation purposes, it is checked whether the returned label is contained in the labels of the ground truth. On this dataset, MNB achieves a lower macro-average F1-score which is 0.59.\footnote{The code for this is available at \href{https://great-ai.scoutinscience.com/examples/simple/deploy}{great-ai.scoutinscience.com/examples/simple/deploy}.} The weighted-average F1 is 0.70, and the overall accuracy is also 70\%. The substantial difference between the macro and weighted averages comes from the unbalanced distribution of the labels.
+Since Multinomial Naïve Bayes is best at returning a single label and SSC has multiple labels per datapoint: for evaluation purposes, it is checked whether the returned label is contained in the labels of the ground truth. On this dataset, MNB achieves a lower macro-average F1 score of 0.59.\footnote{The code for this is available at \href{https://great-ai.scoutinscience.com/examples/simple/deploy}{great-ai.scoutinscience.com/examples/simple/deploy}.} The weighted-average F1 is 0.70, and the overall accuracy is also 70\%. The substantial difference between the macro and weighted averages comes from the unbalanced distribution of the labels.
-The lower F1-score is not surprising because there are more than twice as many classes in this dataset. Additionally, the mistakes made are defensible when we look at Figure \ref{fig:ss-confusion}: most of them are between close or related classes.
+The lower F1 score is not surprising because this dataset has more than twice as many classes. Additionally, the mistakes made are defensible when we look at Figure \ref{fig:ss-confusion}: most of them are between close or related classes.
\begin{displayquote}
-This is the usual point where papers conclude: a proof-of-concept/prototype has been built and its performance demonstrated, measured --- and usually --- explained. Nonetheless, in an industrial setting, our problem is far from being solved: it has yet to be deployed.
+This is the usual point where papers conclude: a proof-of-concept/prototype has been built, and its performance demonstrated, measured --- and usually --- explained. Nonetheless, in an industrial setting, our problem is far from being solved: it has yet to be deployed.
\end{displayquote}
\subsection{Deployment}
-First, an inference function needs to be written that can take input on the fly and calculate a corresponding prediction. Since we aim to follow the best practices, namely: \textit{Explain Results and Decisions to Users} and \textit{Employ Interpretable Models When Possible}, giving an explanation of the results is expected. Fortunately, with our simple model, it is easy to determine the most influential weights, thus, words. The explanations are derived by taking the top 5 tokens from the input text ranked by their feature weights. The last deployment step may be to provide access to our model for others.
+First, an inference function needs to be written that can take input on the fly and calculate a corresponding prediction. Since we aim to follow the best practices, namely: \textit{Explain Results and Decisions to Users} and \textit{Employ Interpretable Models When Possible}, explaining the results is expected. Fortunately, with our simple model, it is easy to determine the most influential weights, thus, words. The explanations are derived by taking the top 5 tokens from the input text ranked by their feature weights. The last deployment step may be to provide access to our model for others.
\begin{displayquote}
-\textbf{How do we provide an interface for the inference function?} We either have an offline or online inference workflow (or both). For the former, we have to provide a way to use it in batch processing; a simple Python function may be adequate for this purpose, though allowing it to be easily (or automatically) parallelised would make its consumers' DX better. If it is an online workflow, we must have a service running continuously and accepting input at any time. This can be achieved by a remote procedure call (RPC) interface or more commonly, a web API. Developers usually refer to these as REST APIs, sometimes, they even follow the conventions of REST. Either way, we must develop a wrapper over the service in order to make it available for other internal/external consumers.
+\textbf{How do we provide an interface for the inference function?} We either have an offline or online inference workflow (or both). For the former, we have to provide a way to use it in batch processing; a simple Python function may be adequate for this purpose, though allowing it to be easily (or automatically) parallelised would improve its consumers' DX. If it is an online workflow, we must have a service running continuously and accepting input at any time. This can be achieved by a remote procedure call (RPC) interface or, more commonly, a web API. Developers usually refer to these as REST APIs, and sometimes, they even follow the conventions of REST. Either way, we must develop a wrapper over the service to make it available to other internal/external consumers.
\end{displayquote}
-According to the body of research on the adoption of best practices, this is where many real-world projects conclude. This also happens to be \textbf{the gap}. Believing that solely focusing on the research and experiments is good enough is a fallacy: when following this approach, the deployment step ends up being a rushed attempt of wrapping the \textit{AI} and putting it in the production environment. This is inarguably a deployment. However, it likely follows very few of the best practices, which can lead to suboptimal real-life performance, lack of accountability, lack of opportunity to improve, and possibly an overall negative societal impact.
+According to the body of research on the adoption of best practices, this is where many real-world projects conclude. This also happens to be \textbf{the gap}. Believing that solely focusing on the research and experiments is good enough is a fallacy: when following this approach, the deployment step ends up being a rushed attempt of wrapping the \textit{AI} and putting it in the production environment. This is, inarguably, a deployment. However, it likely follows very few of the best practices, which can lead to suboptimal real-life performance, lack of accountability, lack of opportunity to improve, and possibly an overall negative societal impact.
\begin{displayquote}
\textbf{How could we implement more best practices?} The most notable missing software/operations features are the lack of automated deployment, automated regression testing, online monitoring, persisting the traces, graceful error-handling, taking feedback on the results (if possible in the use-case), calculating the online accuracy based on the feedback, and retraining the model if necessary using novel data. These all correspond to best practices.
@@ -106,31 +106,31 @@ According to the body of research on the adoption of best practices, this is whe
\section{Bridging the gap with GreatAI}
-First, let us revisit the library's scope for clarification. As concluded in Section \ref{section:scope}, \textit{GreatAI} should ease the \textit{transition} step between prototypes and production-ready deployments. However, this leaves open the question of what constitutes to this step? There are cross-cutting concerns, for example, feature extraction is implemented and used in the training phase, but it is also deployed alongside the model. The robustness criterion has to be met by this procedure even though its implementation is only in focus in the earlier stages of the project. Since having an untested function deployed into production can have severe repercussions, I conclude, assuring its correctness lies within the scope of \textit{GreatAI}.
+First, let us revisit the library's scope for clarification. As concluded in Section \ref{section:scope}, \textit{GreatAI} should ease the \textit{transition} step between prototypes and production-ready deployments. However, this leaves open the question of what constitutes this step. There are cross-cutting concerns; for example, feature extraction is implemented and used in the training phase, but it is also deployed alongside the model. The robustness criterion has to be met by this procedure even though its implementation is only in focus in the earlier stages of the project. Since having an untested function deployed into production can have severe repercussions, I conclude, assuring its correctness lies within the scope of \textit{GreatAI}.
-This section briefly explores how the problems raised can be solved using \textit{GreatAI}, and the API it provides in order to best fit the needs of its users. We first focus on the aspects of data, then we discuss the utility of helper functions, and lastly, the automated wrapping of services.
+This section briefly explores how the problems raised can be solved using \textit{GreatAI} and the API it provides to best fit the needs of its users. We first focus on the aspects of data, then we discuss the utility of helper functions, and lastly, the automated wrapping of services.
\subsection{Handling data} \label{subsection:large-file}
-The obstacles coming from the intertwined nature of different models is widely recognised \cite{haakman2021ai,amershi2019software,sculley2015hidden}. This can lead to non-monotonic error propagation, meaning that improvements in one part of the system might decrease the overall system quality \cite{amershi2019software}. The importance of schema versioning in an environment of rapidly changing models and transformations is highlighted for a specific use-case in \cite{van2017versioning} and more generally by the \textit{Use Versioning for Data, Model, Configurations and Training Scripts} best practice. These emphasise the requirement for versioning models and, in general, data.
+The obstacles coming from the intertwined nature of different models are widely recognised \cite{haakman2021ai,amershi2019software,sculley2015hidden}. This can lead to non-monotonic error propagation, meaning that improvements in one part of the system might decrease the overall system quality \cite{amershi2019software}. The importance of schema versioning in an environment of rapidly changing models and transformations is highlighted for a specific use-case in \cite{van2017versioning} and more generally by the \textit{Use Versioning for Data, Model, Configurations and Training Scripts} best practice. These emphasise the requirement for versioning models and, in general, data.
-There are two kinds of data storage needs we have to address: training data and trained models. Because our code is probably already tracked under Git (and \href{https://octoverse.github.com/#lets-look-back-at-the-code-and-communities-built-on-git-hub-this-year}{likely synchronised with GitHub}), using the Git Large File Storage (LFS)\footnote{\href{https://git-lfs.github.com/}{git-lfs.github.com}} might seem intriguing. However, it is a paid (and surprisingly expensive) service of GitHub, especially when we factor in the expected sizes of the models and training data with the fact that the only way to remove files counting towards our quota is to \href{https://docs.github.com/en/repositories/working-with-files/managing-large-files/removing-files-from-git-large-file-storage#git-lfs-objects-in-your-repository}{delete the entire repository}.
+We have to address two kinds of data storage needs: training data and trained models. Because our code is probably already tracked under Git (and \href{https://octoverse.github.com/#lets-look-back-at-the-code-and-communities-built-on-git-hub-this-year}{likely synchronised with GitHub}), using the Git Large File Storage (LFS)\footnote{\href{https://git-lfs.github.com/}{git-lfs.github.com}} might seem intriguing. However, it is a paid (and surprisingly expensive) service of GitHub, especially when we factor in the expected sizes of the models and training data with the fact that the only way to remove files counting towards our quota is to \href{https://docs.github.com/en/repositories/working-with-files/managing-large-files/removing-files-from-git-large-file-storage#git-lfs-objects-in-your-repository}{delete the entire repository}.
-An open-source tool, the Data Version Control (DVC)\footnote{\href{https://dvc.org/}{dvc.org}} provides a nearly perfect alternative. It comes with a command-line interface (CLI) inspired by Git's, and it can be integrated with several backend storage servers. Its only downside is, of course, that it is one more tool that increases the complexity of the project and the initial setup time. If this is an acceptable price to pay, then I personally recommend opting for DVC. Nevertheless, if this may prohibit a team\footnote{As was the case with MLFlow tracking in an ING team described in Section \ref{section:industry}.} from properly handling data according to the best practices, I present a simpler solution.
+An open-source tool, the Data Version Control (DVC)\footnote{\href{https://dvc.org/}{dvc.org}} provides a nearly perfect alternative. It comes with a command-line interface (CLI) inspired by Git's and can be integrated with several backend storage servers. Its only downside is, of course, that it is one more tool that increases the complexity of the project and the initial setup time. If this is an acceptable price to pay, then I personally recommend opting for DVC. Nevertheless, if this may prohibit a team\footnote{As was the case with MLFlow tracking in an ING team described in Section \ref{section:industry}.} from properly handling data according to the best practices, I present a simpler solution.
-The complexity of an API can be decreased by relying on its users' preexisting knowledge and known patterns \cite{hermans2021programmer,ousterhout2018philosophy}. Therefore, we can reuse familiar APIs, such as the \texttt{open()} method from Python. Therefore, a method is proposed which provides the same interface; however, the backing storage can be a mixture of local disk space, S3-compatible storage, MongoDB, or any other storage backend. It provides a superset of \texttt{open()}'s interface\footnote{\href{https://docs.python.org/3/library/functions.html\#open}{docs.python.org/3/library/functions.html\#open}}: the same parameters can be used with it resulting in similar observed behaviour. The expected features: versioning, progress bars, caching, garbage collecting the cache, and automatically deleting old remote versions are all present and come with recommended --- but easy to see and change --- configuration.
+The complexity of an API can be decreased by relying on its users' preexisting knowledge, and known patterns \cite{hermans2021programmer,ousterhout2018philosophy}. Therefore, we can reuse familiar APIs, such as the \texttt{open()} method from Python. Therefore, a method is proposed which provides the same interface; however, the backing storage can be a mixture of local disk space, S3-compatible storage, MongoDB, or any other storage backend. It provides a superset of \texttt{open()}'s interface\footnote{\href{https://docs.python.org/3/library/functions.html\#open}{docs.python.org/3/library/functions.html\#open}}: the same parameters can be used with it resulting in similar observed behaviour. The expected features: versioning, progress bars, caching, garbage collecting the cache, and automatically deleting old remote versions are all present and come with recommended --- but easy to see and change --- configuration.
Easing development is not merely about automating everything but also about making the code easy to change (which is the \textit{Viscosity} dimension of CDCB). Going from opening a local file on the disk with the built-in open method, to opening a file from S3 is as easy as changing \texttt{open('file.txt', 'w')} to \texttt{LargeFileS3('file.txt', 'w')}. In the case of the latter, an additional \texttt{version} keyword argument can also be given to lock ourselves in using a certain version which is very much desired in the case of models.
\subsection{Utilities}
-It is easy to notice multiple recurring tasks when it comes to processing text. Cleaning it from various extraction artifacts and normalising characters is one of the most common. But splitting sentences, language tagging, and robustly lemmatizing are also often recurring tasks. Because having reusable and tested feature extraction code covers two best practices, it seems straightforward that a utility module could be created for this, which could be extensively tested through unit testing.
+It is easy to notice multiple recurring tasks when it comes to processing text. Cleaning it from various extraction artifacts and normalising characters is one of the most common. But splitting sentences, language tagging, and robustly lemmatising are also often recurring tasks. Because having reusable and tested feature extraction code covers two best practices, it seems straightforward that a utility module could be created for this, which could be extensively tested through unit testing.
This is exactly the motivation behind \texttt{great\_ai.utilities}. Extra care has to be taken not to overfit these utilities on the cases considered in this chapter; however, I believe these are versatile enough to be helpful in many text-related contexts. A conclusive answer to this assumption will be found during the interviews.
Implementing the unit tests uncovered multiple edge cases and even runtime errors; hence, the merit of \textit{Test all Feature Extraction Code} best practice is unequivocal. There is one more best practice that could be partially covered here, especially because its solution also helps both during batch inference but also at training/feature extraction time: \textit{Enable Parallel Training Experiments}.
-A function called \texttt{parallel\_map()} is implemented which closely mimics the API of the built-in Python function: \texttt{map}. And it exemplifies how even a close to trivial function is able to improve the DX by magnitudes. Rooted in the global interpreter lock (GIL)\footnote{\href{https://wiki.python.org/moin/GlobalInterpreterLock}{wiki.python.org/moin/GlobalInterpreterLock}} of CPython, in almost all cases, multi-threading does not lead to higher performance of CPU-bound tasks. For this purpose, multiprocessing has to be used. Fortunately, the built-in \texttt{multiprocessing} library has a great API. However, doing a parallel mapping task with a progress bar still takes about a dozen lines. This can deter people (at least me) from taking advantage of more than just a single CPU core during exploratory experimentation. With \texttt{parallel\_map()}, this challenge becomes a single-line, routine task.
+A function called \texttt{parallel\_map()} is implemented which closely mimics the API of the built-in Python function: \texttt{map}. Furthermore, it exemplifies how even a close to trivial function can improve the DX by magnitudes. Rooted in the global interpreter lock (GIL)\footnote{\href{https://wiki.python.org/moin/GlobalInterpreterLock}{wiki.python.org/moin/GlobalInterpreterLock}} of CPython, in almost all cases, multi-threading does not lead to higher performance of CPU-bound tasks. For this purpose, multiprocessing has to be used. Fortunately, the built-in \texttt{multiprocessing} library has a great API. However, doing a parallel mapping task with a progress bar still takes about a dozen lines. This can deter people (at least me) from taking advantage of more than just a single CPU core during exploratory experimentation. With \texttt{parallel\_map()}, this challenge becomes a single-line, routine task.
\subsection{Deployment approach}
@@ -139,7 +139,7 @@ In line with the findings of John et al. \cite{john2020architecting} on the SOTA
Based on personal empirical evidence, three types of software artifacts are identified (in the context of Python) for which a wide range of established practices exist. WSGI server\footnote{\href{https://peps.python.org/pep-3333/}{peps.python.org/pep-3333}} compatible applications, executable scripts, and Docker Images\footnote{\href{https://docs.docker.com/registry/spec/manifest-v2-2/}{docs.docker.com/registry/spec/manifest-v2-2}}. To achieve this, \textit{GreatAI} provides a compatibility layer between simple Python inference functions and all the above common artifacts. Taking functions as input for the first step also satisfies the requirement to be \textbf{General}. Nevertheless, to also allow customisation, additional configuration, metadata, and behavioural specification can be given as well.
-The main advantage of the wrapping approach is that it does not require any input from the clients (by default). I opted for a decorator \cite{gamma1995design}, which lets users wrap their function by adding a single additional line of code as shown in Listing \ref{listing:hello-world}. After which, the created WSGI application can be accessed through the \texttt{greeter.app} property where \texttt{greeter} is the identifier of the user-defined function. A CLI script (\texttt{great-ai}), along with a \texttt{Dockerfile} are also provided to cover the other two deployment artifacts.
+The main advantage of the wrapping approach is that it does not require any input from the clients (by default). I opted for a decorator \cite{gamma1995design}, which lets users wrap their function by adding a single additional line of code as shown in Listing \ref{listing:hello-world}. After which, the created WSGI application can be accessed through the \texttt{greeter.app} property where \texttt{greeter} is the identifier of the user-defined function. A CLI script (\texttt{great-ai}), along with a \texttt{Dockerfile} are also provided to cover the other two deployment artifacts.
\begin{listing}[!ht]
\begin{minted}[
diff --git a/thesis/chapters/5_cases/scibert.tex b/thesis/chapters/5_cases/scibert.tex
index ec35483..058be4e 100644
--- a/thesis/chapters/5_cases/scibert.tex
+++ b/thesis/chapters/5_cases/scibert.tex
@@ -2,37 +2,37 @@
The ScoutinScience Dashboard contains a full-page evaluation view for academic publications. On this, the known metadata, historical trends about the paper's topics, social media mentions, a PDF viewer showing the document, and other augmentation tools are displayed. One of these is the \textit{Highlights} section, which aims to summarise the paper from a technology-transfer perspective.
-The current approach uses a simple heuristic based on a set of phrases selected by business developers and extended with the help of a word2vec model \cite{mikolov2013efficient}. The user feedback deemed this implementation slightly helpful but inadequate for providing an accurate overview. Thus, this is the baseline that I attempt to improve on in this section.
+The current approach uses a simple heuristic based on a set of phrases selected by business developers and extended with the help of a word2vec model \cite{mikolov2013efficient}. The user feedback deemed this implementation slightly helpful but inadequate for providing an accurate overview. Thus, this is the baseline I attempt to improve on in this section.
\begin{displayquote}
-Compared with Section \ref{section:simple-case}, this time around, the toolset of \textit{GreatAI} is available at our disposal. Hopefully, this will streamline the development and --- especially --- the deployment. Given its arguably higher complexity, the experiment falls closer to industrial use cases, and hence, can give more accurate feedback on how to further improve the API.
+Compared with Section \ref{section:simple-case}, this time around, the toolset of \textit{GreatAI} is available at our disposal. Hopefully, this will streamline the development and --- especially --- the deployment. Given its arguably higher complexity, the experiment falls closer to industrial use cases and hence, can give more accurate feedback on how to further improve the API.
\end{displayquote}
\subsection{Background}
Automatic text summarisation (ATS) is also one of the earliest established tasks of text analysis and boasts numerous promising results \cite{el2021automatic}. Text summarisation is usually divided into extractive and abstractive approaches. Even though the latter can lead to more fluent summaries, it is also prone to hallucinate content that is unfaithful to the input \cite{maynez2020faithfulness}. For this reason, extractive techniques are preferred in this case.
-Our problem requires generating a special type of summary: it must only concern a single aspect (tech transfer) of the document. Aspect-based text summarisation has also seen some progress over the last decades \cite{berkovsky2008aspect,hayashi2021wikiasp} but these methods require concretely defined topics. Unfortunately, \textit{tech-transfer potential} is anything but a clear topic definition.
+Our problem requires generating a special type of summary: it must only concern a single aspect (tech transfer) of the document. Aspect-based text summarisation has also seen some progress over the last decades \cite{berkovsky2008aspect,hayashi2021wikiasp}, but these methods require concretely defined topics. Unfortunately, \textit{tech-transfer potential} is anything but a clear topic definition.
-Numerous discussions and interviews with business developers over the last two years made it clear that there is no universally agreed-on definition of it. At least, all of them agree that they know it when they see it. Additionally, most of them agree that they can confidently make a decision on the granularity of sentences. This gives rise to an obvious idea: show the experts something they can annotate. Because experts' time is valuable, and relevant sentences are few and far between, extra care needs to be taken to improve the ratio of positive examples in the dataset. The research of Iwatsuki Kenichi on formulaic expressions (FEs) \cite{iwatsuki2020evaluation,iwatsuki2021extraction,iwatsuki2021communicative,iwatsuki2022extraction} provides a promising direction to do so.
+Numerous discussions and interviews with business developers over the last two years made it clear that there is no universally agreed-on definition of it. At least all of them agree that they know it when they see it. Additionally, most of them agree that they can confidently make a decision on the granularity of sentences. This gives rise to an obvious idea: show the experts something they can annotate. Because experts' time is valuable, and relevant sentences are few and far between, extra care needs to be taken to improve the ratio of positive examples in the dataset. The research of Iwatsuki Kenichi on formulaic expressions (FEs) \cite{iwatsuki2020evaluation,iwatsuki2021extraction,iwatsuki2021communicative,iwatsuki2022extraction} provides a promising direction to do so.
-A formulaic expression is a phrase with zero or more ``slots'' which, when filled appropriately, leads to expressing a certain intent. In the context of scientific text, an example\footnote{Taken from the ground-truth data available at \href{https://github.com/Alab-NII/FECFevalDataset/blob/master/human_evaluation/background.tsv}{github.com/Alab-NII/FECFevalDataset}.} could be: \texttt{it was not until * that}. The asterisk can be substituted with multiple terms and the intention of this expression is (likely) to describe the \textit{History of the related topics}. Iwatsuki et al. identified a set of 39 intentions, compiled a manually labelled dataset \cite{iwatsuki2020evaluation}, and developed multiple approaches for automatically extracting and classifying formulaic expressions in large corpora \cite{iwatsuki2021communicative,iwatsuki2022extraction}.
+A formulaic expression is a phrase with zero or more ``slots'' which, when filled appropriately, leads to expressing a certain intent. In the context of scientific text, an example\footnote{Taken from the ground-truth data available at \href{https://github.com/Alab-NII/FECFevalDataset/blob/master/human_evaluation/background.tsv}{github.com/Alab-NII/FECFevalDataset}.} could be: \texttt{it was not until * that}. The asterisk can be substituted with multiple terms, and the intention of this expression is (likely) to describe the \textit{History of the related topics}. Iwatsuki et al. identified a set of 39 intentions, compiled a manually labelled dataset \cite{iwatsuki2020evaluation}, and developed multiple approaches for automatically extracting and classifying formulaic expressions in large corpora \cite{iwatsuki2021communicative,iwatsuki2022extraction}.
\subsection{Methods}
-In order to compile a new dataset, experts are asked to judge sentences that passed an \textit{intention check}. This pooling approach is commonly used in the field of information retrieval \cite{schutze2008introduction}. The filtering is expected to sieve out sentences that are probably not relevant from a technology-transfer perspective using Iwatsuki's formulaic expression intention classes. Subsequently, relevance judgements --- in the form of \textit{interesting} or \textit{not interesting} labels --- are gathered for the remaining sentences. This method turns the extractive summarisation into a binary classification task for which a SciBERT model \cite{beltagy2019scibert} can be finetuned. Ultimately, the summaries are derived from sentences that are selected by the classifier trained on the experts' annotations.
+In order to compile a new dataset, experts are asked to judge sentences that passed an \textit{intention check}. This pooling approach is commonly used in information retrieval \cite{schutze2008introduction}. The filtering is expected to sieve out sentences that are probably not relevant from a technology-transfer perspective using Iwatsuki's formulaic expression intention classes. Subsequently, relevance judgements --- in the form of \textit{interesting} or \textit{not interesting} labels --- are gathered for the remaining sentences. This method turns the extractive summarisation into a binary classification task for which a SciBERT model \cite{beltagy2019scibert} can be fine-tuned. Ultimately, the summaries are derived from sentences selected by the classifier trained on the experts' annotations.
We have to note two possible shortcomings of this setup: firstly, the FE intentions are assumed to be strongly correlated with the sought-after aspect. This may or may not be true. Secondly, only the individual relevance of the sentences is considered instead of the overall relevance (utility) of the summary. Nonetheless, it is expected that stemming from the length of the documents and the sparseness of the selected sentences, that any combination of them is likely to have low redundancy.
\subsection{Results}
-For the first iteration, 1500 sentences were selected for 2 experts to annotate in a binary fashion according to strict guidelines. An example is shown in Figure \ref{fig:annotator}. Afterwards, for measuring the interrater agreement, Cohen's kappa \cite{cohen1960coefficient} is calculated as shown in Equation \ref{equation:kappa}. Which turns out to be \textbf{0.4310} for the two annotators. This happens to be just above the lower end of \textit{moderate agreement}. However, we have to note that the original quality ranges are often criticised for being too relaxed \cite{mchugh2012interrater}. However, in the case of summarisation, Verberne et al. \cite{verberne2018creating} argue that reasonable end-quality can be reached even when the interrater agreement is relatively low. The ground truth is determined by taking the logical disjunction of the annotations.
+For the first iteration, 1500 sentences were selected for two experts to annotate in a binary fashion according to strict guidelines. An example is shown in Figure \ref{fig:annotator}. Afterwards, for measuring the interrater agreement, Cohen's kappa \cite{cohen1960coefficient} is calculated as shown in Equation \ref{equation:kappa}, which turns out to be \textbf{0.4310} for the two annotators. This happens to be just above the lower end of \textit{moderate agreement}. However, we have to note that the original quality ranges are often criticised for being too relaxed \cite{mchugh2012interrater}. However, in the case of summarisation, Verberne et al. \cite{verberne2018creating} argue that reasonable end-quality can be reached even when the interrater agreement is relatively low. The ground truth is determined by taking the logical disjunction of the annotations.
\begin{figure}
\centering
\includegraphics[width=0.75\linewidth]{figures/annotator.png}
\captionsetup{width=.9\linewidth}
- \caption{Annotator UI showing a single sentence and the two possible labels that can be assigned based on its relevance to technology transfer.}
+ \caption{The Annotator UI shows a single sentence and the two possible labels that can be assigned based on its relevance to technology transfer.}
\label{fig:annotator}
\end{figure}
@@ -40,17 +40,17 @@ For the first iteration, 1500 sentences were selected for 2 experts to annotate
\kappa_{agreement} \equiv \frac{p_{observed} - p_{expected}}{1 - p_{expected}} = 1 - \frac{1 - p_{observed}}{1 - p_{expected}}
\end{equation}
-The next step is finetuning SciBERT with the help of HuggingFace transformers \cite{wolf2019huggingface}. The data are divided into training and test splits with a ratio of 4:1. From the train split, a validation split is also derived, which is used for early stopping. The objective function is the F1-score of the positive class and the early stopping patience is 5 epochs. The learning rate is $5 \times 10^{-5}$ and AdamW \cite{loshchilov2017decoupled} is used for optimisation with a weight decay of 0.05. The code can be found in the documentation\footnote{\href{https://great-ai.scoutinscience.com/examples/scibert/train/}{great-ai.scoutinscience.com/examples/scibert/train}}, it is surprisingly slightly shorter than the code of Section \ref{section:simple-case}.
+The next step is fine-tuning SciBERT with the help of HuggingFace transformers \cite{wolf2019huggingface}. The data are divided into training and test splits with a ratio of 4:1. A validation split, used for early stopping, is also derived from the train split. The objective function is the F1-score of the positive class, and the early stopping patience is five epochs. The learning rate is $5 \times 10^{-5}$ and AdamW \cite{loshchilov2017decoupled} is used for optimisation with a weight decay of 0.05. The code can be found in the documentation\footnote{\href{https://great-ai.scoutinscience.com/examples/scibert/train/}{great-ai.scoutinscience.com/examples/scibert/train}}, it is surprisingly slightly shorter than the code of Section \ref{section:simple-case}.
\begin{displayquote}
-\textbf{Reproducibility} Reproducible experiments are generally preferred. It is easy to forget to set some seed values and, for example, end up with different datapoints in the test-train splits during training and validation in a Continuous Integration (CI) pipeline. To facilitate reproducibility, it would be useful to reset the seeds of each imported library's random number generators (RNGs) when \textit{GreatAI} is configured. Thus, a feature has been added to detect and reset RNGs of installed and imported libraries. This certainly will not solve the reproducibility crisis \cite{hutson2018artificial} on its own, however, in some cases, it can result in one fewer step to miss.
+\textbf{Reproducibility} Reproducible experiments are generally preferred. It is easy to forget to set some seed values and, for example, end up with different data points in the test-train splits during training and validation in a Continuous Integration (CI) pipeline. For facilitating reproducibility, it would be useful to reset the seeds of each imported library's random number generators (RNGs) when \textit{GreatAI} is configured. Thus, a feature has been added to detect and reset RNGs of installed and imported libraries. This certainly will not solve the reproducibility crisis \cite{hutson2018artificial} on its own; however, in some cases, it can result in one fewer step to miss.
\end{displayquote}
\begin{displayquote}
-\textbf{Utility of LargeFiles} For the purposes of the documentation, the finetuning was conducted in the Google Colab online environment, which is excellent for providing anyone with GPU time for free. However, notebook environments are ephemeral, resulting in the need to manually upload and download all relevant data whenever a new virtual machine (VM) instance is granted. The \texttt{LargeFile} implementation alleviated this problem by handling the uploads and downloads automatically. Of course, first, backwards compatibility had to be solved for Python 3.7, which is the only available environment in Colab.
+\textbf{Utility of LargeFiles} For the purposes of the documentation, the fine-tuning was conducted in the Google Colab online environment, which is excellent for providing anyone with GPU time for free. However, notebook environments are ephemeral, resulting in the need to manually upload and download all relevant data whenever a new virtual machine (VM) instance is granted. The \texttt{LargeFile} implementation alleviated this problem by automatically handling the uploads and downloads. Of course, first, backwards compatibility had to be solved for Python 3.7, the only available environment in Colab.
\end{displayquote}
-The best validation results were achieved after 8 epochs which is slightly more than expected but is presumably due to the weight decay. The confusion matrix on the test split can be seen in Figure \ref{fig:scibert-confusion}: regardless of the subjective definition of the task, SciBERT manages to achieve good quality which is indicated by an F1-score of \textbf{0.89}.
+The best validation results were achieved after eight epochs which is slightly more than expected but is presumably due to the weight decay. The confusion matrix on the test split can be seen in Figure \ref{fig:scibert-confusion}: regardless of the task's subjective definition, SciBERT achieves good quality, which is indicated by an F1-score of \textbf{0.89}.
\begin{figure}
\centering
@@ -62,7 +62,7 @@ The best validation results were achieved after 8 epochs which is slightly more
Let us check how well the selected sentences correspond with the tech-transfer potential. Users and in-house experts can rate publications (from a tech-transfer perspective) by assigning them to one of four categories: \texttt{A}, \texttt{B}, \texttt{C}, and \texttt{D} with \texttt{A} being the most and \texttt{D} the least promising. This feedback is stored and used for analytic and training purposes. Since both the feedback grade and the ``highlights'' are supposed to reflect the same aspect of papers, therefore, we can reasonably expect some correlation between them.
-Figure \ref{fig:histograms} shows the ratio of summary candidate sentences as predicted by the finetuned model in 4 categories (grades) of papers. The two datasets come from non-overlapping sets of papers; hence, the results come solely from the model's ability to generalise. It is interesting to see that the Spearman's rank correlation coefficient \cite{spearman1961proof} between the normalised ``highlights'' counts and the ratings of papers is \textbf{0.4784} and is statistically significant ($P = 5.4 \times 10^{-74}$). This proves the presence of a monotonic association. For context, the correlation between the grades and the number of sentences found by the baseline approach is 0.06597 ($P = 0.03$). We can conclude that the classifier's output is indicative of publications' tech-transfer potential.
+Figure \ref{fig:histograms} shows the ratio of summary candidate sentences as predicted by the fine-tuned model in 4 categories (grades) of papers. The two datasets come from non-overlapping sets of papers; hence, the results come solely from the model's ability to generalise. It is interesting to see that the Spearman's rank correlation coefficient \cite{spearman1961proof} between the normalised ``highlights'' counts and the ratings of papers is \textbf{0.4784} and is statistically significant ($P = 5.4 \times 10^{-74}$). This proves the presence of a monotonic association. For context, the correlation between the grades and the number of sentences found by the baseline approach is 0.06597 ($P = 0.03$). We can conclude that the classifier's output is indicative of publications' tech-transfer potential.
\begin{figure}
\centering
@@ -74,7 +74,7 @@ Figure \ref{fig:histograms} shows the ratio of summary candidate sentences as pr
\subsection{Deployment}
-To implement the summarisation, at most, the top 7 selected sentences are chosen as ranked by their log-probabilities. They are subsequently reordered according to their position in the text. As a quasi-explanation, the tokens' attention scores are visualised and overlaid on the highlighted sentences. The \textit{i}-th token's visualised attention comes from summing up the attention weights of each of the last layer's heads between the \texttt{[CLS]} and the \textit{i}-th token. To improve the end-user experience, a high-pass filter and a stop-word list is applied to the scores in order not to highlight the syntax-related tokens (punctuation, determiners). The service --- after being integrated into the dashboard --- can be seen in Figure \ref{fig:dashboard-highlights}.
+To implement the summarisation, at most, the top 7 selected sentences are chosen as ranked by their log probabilities. They are subsequently reordered according to their position in the text. As a quasi-explanation, the tokens' attention scores are visualised and overlaid on the highlighted sentences. The \textit{i}-th token's visualised attention comes from summing up the attention weights of each of the last layer's heads between the \texttt{[CLS]} and the \textit{i}-th token. To improve the end-user experience, a high-pass filter and a stop-word list are applied to the scores to avoid highlighting the syntax-related tokens (punctuation, determiners). The service --- after being integrated into the dashboard --- can be seen in Figure \ref{fig:dashboard-highlights}.
\begin{displayquote}
\textbf{Design inspiration} In order to get insights into their inner workings, HuggingFace models can be given \texttt{output\_attentions=True} in their constructor, which results in a new property becoming accessible on the results for querying the attentions. The only issue with it is that it is a 5-dimensional matrix which makes exploring and understanding it non-obvious. In short, it has very low \textit{Discoveribility}. For example, the attention weights for the UI are calculated with this expression:
@@ -83,7 +83,7 @@ baselinestretch=1,
]{python}
np.sum(result.attentions[-1].numpy()[0], axis=0)[0][1:-1]
\end{minted}
-Even though the operation is conceptually simple, because of the opaque data structure, this is anything but obvious to comprehend. Therefore, it is clear that this needs to be avoided in my library design; it has to have an explicit and discoverable API which can be achieved by the use of type hints, descriptive property names, and docstrings.
+Even though the operation is conceptually simple, because of the opaque data structure, this is anything but obvious to comprehend. Therefore, it is clear that this needs to be avoided in my library design; it has to have an explicit and discoverable API that can be achieved by using type hints, descriptive property names, and docstrings.
\end{displayquote}
\begin{figure}
@@ -104,7 +104,7 @@ Sustainability is an increasingly crucial concern of ethical AI \cite{van2021sus
\subsection{Revisiting \texttt{parallel\_map}}
-Even though most inference functions are CPU-bound, it turns out that sometimes they involve IO, especially when relying on the results of other remote models. This means a significant performance improvement can be achieved by implementing some inference functions asynchronously \cite{tilkov2010node}. Thus, \textit{GreatAI} also has to support decorating both regular (synchronous) and asynchronous functions. One notable consequence of this is that the batch processing feature also has to be compatible with \texttt{async} inference functions. Batch processing is still a helpful feature since it is likely that async inference functions are both IO (remote calls) and CPU (local evaluation) constrained at the same time. Thus, they can benefit from multi-core parallelisation.
+Even though most inference functions are CPU-bound, it turns out that sometimes they involve IO, especially when relying on the results of other remote models. This means a significant performance improvement can be achieved by implementing some inference functions asynchronously \cite{tilkov2010node}. Thus, \textit{GreatAI} also has to support decorating both regular (synchronous) and asynchronous functions. One notable consequence is that the batch processing feature must also be compatible with \texttt{async} inference functions. Batch processing is still a helpful feature since it is likely that async inference functions are both IO (remote calls) and CPU (local evaluation) constrained at the same time. Thus, they can benefit from multi-core parallelisation.
However, the standard library's \texttt{multiprocessing}, the third party \texttt{multiprocess} \cite{mckerns2012building}, and, another popular library, \texttt{joblib}\footnote{\href{https://joblib.readthedocs.io/en/latest/}{joblib.readthedocs.io/en/latest}} all lack the support for efficiently parallelising async functions. For this reason, \texttt{parallel\_map} is reimplemented to create an event-loop in each worker process to keep the efficiency of non-blocking IO while also providing parallelisation for the CPU-bound sections of code.
@@ -112,7 +112,7 @@ However, the standard library's \texttt{multiprocessing}, the third party \textt
Apart from supporting \texttt{async} calls, a couple more steps can be taken to help integrate any service with a \textit{GreatAI} deployment. This is implemented by the \texttt{call\_remote\_great\_ai} function which hides the networking required to call a \textit{GreatAI} instance's REST API. It takes care of validation, automatic retries, serialisation, and deserialisation. This comes with the added benefit of encouraging decoupled services because the friction of integrating them is no longer noticeable, which is beneficial for human collaboration \cite{hasselbring2002component}.
-Additionally, a REST API is generated with its accompanying OpenAPI schema\footnote{\href{https://swagger.io/specification}{swagger.io/specification}} and served with a \href{https://swagger.io/}{Swagger} template. It also contains metadata about the function, for instance, its docstring, version, and version of its registered models concatenated in order to be SemVer\footnote{\href{https://semver.org/}{semver.org}} compatible. These can be seen in Figure \ref{fig:greatai-api}. This, combined with a \texttt{/version} HTTP endpoint for programmatic access and validation of the service's metadata, proved to be key features when integrating the \textit{Highlights service} into ScoutinScience's service-based architecture.
+Additionally, a REST API is generated with its accompanying OpenAPI schema\footnote{\href{https://swagger.io/specification}{swagger.io/specification}} and served with a \href{https://swagger.io/}{Swagger} template. It also contains metadata about the function, for instance, its docstring, version, and version of its registered models concatenated in order to be SemVer\footnote{\href{https://semver.org/}{semver.org}} compatible. These can be seen in Figure \ref{fig:greatai-api}. This, combined with a \texttt{/version} HTTP endpoint for programmatic access and validation of the service's metadata, proved to be critical features when integrating the \textit{Highlights service} into ScoutinScience's service-based architecture.
\begin{figure}
\centering
diff --git a/thesis/chapters/6_results.tex b/thesis/chapters/6_results.tex
index 1b60bf1..f1d6ef2 100644
--- a/thesis/chapters/6_results.tex
+++ b/thesis/chapters/6_results.tex
@@ -1,19 +1,19 @@
-\chapter{Results} \label{chapter:interviews}
+\chapter{Results \& discussion} \label{chapter:interviews}
-It should not be surprising that neither data scientists nor software engineers can be replaced by software libraries. However, a non-negligible subset of their processes can be partially or fully automated, especially, when it comes to packaging and deploying AI/ML services. My goal was to design a library with an API that finds the balance between being simple enough to adopt without friction, yet useful/powerful enough to be adopted. Simplicity is subjective and it will be discussed separately in Section \ref{section:interviews}. For now, let us look at the utility of \textit{GreatAI}.
+It should not be surprising that neither data scientists nor software engineers can be replaced by software libraries. However, a non-negligible subset of their processes can be partially or fully automated, especially when it comes to packaging and deploying AI/ML services. My goal was to design a library with an API that finds the balance between being simple enough to adopt without friction yet useful enough to be adopted. Simplicity is subjective, and it will be discussed separately in Section \ref{section:interviews}. For now, let us look at the utility of \textit{GreatAI}.
\section{Features} \label{section:features}
For answering \textbf{RQ3} --- \textit{To what extent can \textit{GreatAI} automatically implement AI deployment best practices?} --- a comparison is presented in the following that illustrates which best practices can be implemented/scaffolded/configured with little user input; hence, through a simple and streamlined API. Tables \ref{table:best-practices-1} and \ref{table:best-practices-2} summarise the implemented best practices in the context of methods found by prior surveys of scientific and grey literature \cite{serban2020adoption,serban2021practices,john2020architecting}.
-In order to show an accurately nuanced representation, a \textit{Level of support} is determined for each best practice on a scale of \textit{Fully automated}, \textit{Supported}, and \textit{Partially supported}. For instance, \textit{Use static analysis to check code quality} from Table \ref{table:best-practices-1} is \textit{Supported} because the entire public interface of \textit{GreatAI} is correctly typed (including generics and asynchronous coroutines) and compatible with \href{https://mypy.readthedocs.io/en/stable/index.html#}{\texttt{mypy}} and \href{https://marketplace.visualstudio.com/items?itemName=ms-python.vscode-pylance}{\texttt{Pylance}}. This means that when \textit{GreatAI} is used in any Python project, these tools can be applied to statically check the soundness of the project's integration with \textit{GreatAI}. However, if the library's user does not use typehints in their code and it contains a more complex control flow, it can only be partially type-checked. In short, this best practice is supported, and a considerable part of it is already implemented by \textit{GreatAI}, but clients should still keep in mind that they might also need to make effort to fully implement it.
+In order to show an accurately nuanced representation, a \textit{Level of support} is determined for each best practice on a scale of \textit{Partially supported}, \textit{Supported}, and \textit{Fully automated}. For instance, \textit{Use static analysis to check code quality} from Table \ref{table:best-practices-1} is \textit{Supported} because the entire public interface of \textit{GreatAI} is correctly typed (including generics and asynchronous coroutines) and compatible with \href{https://mypy.readthedocs.io/en/stable/index.html#}{\texttt{mypy}} and \href{https://marketplace.visualstudio.com/items?itemName=ms-python.vscode-pylance}{\texttt{Pylance}}. This means that when \textit{GreatAI} is used in any Python project, these tools can be applied to statically check the soundness of the project's integration with \textit{GreatAI}. However, if the library's user does not use type hints in their code and it contains a more complex control flow, it can only be partially type-checked. In short, this best practice is supported, and a considerable part of it is already implemented by \textit{GreatAI}, but clients should still keep in mind that they might also need to make an effort to implement it fully.
-This is not the case for \textit{Log production predictions with the model's version and input data} because by default, it is automatically implemented when calling \texttt{@GreatAI.create}. Users can still specify the exact expected behaviour, e.g.: where to store traces, additional metrics to log, or disabling the logging of sensitive input. Nevertheless, without input from the library's user, the best practice is already reasonably well implemented.
+This is not the case for \textit{Log production predictions with the model's version and input data} because, by default, it is automatically implemented when calling \texttt{@GreatAI.create}. Users can still specify the exact expected behaviour, e.g., where to store traces, additional metrics to log, or disabling the logging of sensitive input. Nevertheless, the best practice is already reasonably well implemented without input from the library's user.
\begin{table}
\centering
\begin{threeparttable}
-\caption{A subset of AI lifecycle best practices and the level of support \textit{GreatAI} provides for them. The level of support is one of \textit{Fully automated} (\checkmark\checkmark) which means that no action is required from the user, \textit{Supported} (\checkmark) only automates the reasonably automatable aspects, while \textit{Partially supported} ($\sim$) provides some useful features but the client is expected to build on top of these.}
+\caption{A subset of AI lifecycle best practices and the level of support \textit{GreatAI} provides for them. The level of support is one of \textit{Fully automated} (\checkmark\checkmark), which means that no action is required from the user, \textit{Supported} (\checkmark) only automates the reasonably automatable aspects, while \textit{Partially supported} ($\sim$) provides some useful features, but the client is expected to build on top of these.}
\label{table:best-practices-1}
{\renewcommand{\arraystretch}{1.2} % for the vertical padding
@@ -48,7 +48,7 @@ Log production predictions with the model's version and input data\textsuperscri
\begin{table}
\centering
\begin{threeparttable}
-\caption{A subset of AI lifecycle best practices and the level of support \textit{GreatAI} provides for them. The level of support is one of \textit{Fully automated} (\checkmark\checkmark) which means that no action is required from the user, \textit{Supported} ($\checkmark$) only automates the reasonably automatable aspects, while \textit{Partially supported} ($\sim$) provides some useful features but the client is expected to build on top of these.}
+\caption{A subset of AI lifecycle best practices and the level of support \textit{GreatAI} provides for them. The level of support is one of \textit{Fully automated} (\checkmark\checkmark), which means that no action is required from the user, \textit{Supported} ($\checkmark$) only automates the reasonably automatable aspects, while \textit{Partially supported} ($\sim$) provides some useful features but the client is expected to build on top of these.}
\label{table:best-practices-2}
{\renewcommand{\arraystretch}{1.2} % for the vertical padding
@@ -57,7 +57,7 @@ Log production predictions with the model's version and input data\textsuperscri
\textbf{Best practice} & \textbf{Implementation} & \textbf{Support} \\\hline
Execute validation techniques: error rates and cross-validation\textsuperscript{2} & \texttt{*\_ground\_truth} & \checkmark \\\hline
% Track models, dependencies, experiments, versions\textsuperscript{2} & \texttt{great\_ai.use\_model}, Dashboard & \checkmark\checkmark \\\hline
-Store models in a single format for ease of use\textsuperscript{2} & \texttt{save\_model} & \checkmark\checkmark \\\hline
+Store models in a single format for o of use\textsuperscript{2} & \texttt{save\_model} & \checkmark\checkmark \\\hline
Rewrite from data analysis to industrial development language\textsuperscript{2} & Jupyter Notebook deployment & \checkmark \\\hline
Equip with web interface, package image, provide REST API\textsuperscript{2} & \texttt{@GreatAI.create} & \checkmark\checkmark \\\hline
Provide simple API for serving batch and real-time requests\textsuperscript{2} & \texttt{@GreatAI.create} & \checkmark\checkmark \\\hline
@@ -87,146 +87,110 @@ Common schemas for common prediction tasks\textsuperscript{3}
\FloatBarrier
-In Table \ref{table:best-practices-2}, six additional best practices have been added which are generally well-known software engineering considerations that are also applicable to AI/ML deployments. These have not explicitly made it into the aforementioned surveys, however, according to the insights gained from Sections \ref{section:simple-case} and \ref{section:complex-case}, implementing them has a positive effect on deployment quality. In future research, attention could be given to their level of industry-wide adoption and quantitative utility.
+In Table \ref{table:best-practices-2}, six additional best practices have been added, which are generally well-known software engineering considerations that are also applicable to AI/ML deployments. These had not explicitly made it into the aforementioned surveys; however, according to the insights gained from Sections \ref{section:simple-case} and \ref{section:complex-case}, implementing them has a positive effect on deployment quality. In future research, attention could be given to their level of industry-wide adoption and quantitative utility.
-Quantifying the number of implemented best practices would be misleading since their scope and importance cover a wide --- sometimes overlapping --- range. Especially because there is some overlap between the different reviews and even within the reviews. However, it is still clear that a large number of best practices can be given a \textit{Fully automated} implementation by \textit{GreatAI}'s design while an even larger number of them can be augmented by the library. This proves the feasibility of designing simple APIs using the techniques of Chapter \ref{chapter:design} for decreasing the complexity of correctly deploying AI services (\textbf{RQ2}).
+Quantifying the number of implemented best practices would be misleading since their scope and importance cover a wide --- sometimes overlapping --- range, especially because there is some overlap between the different studies and even within the studies. However, it is still clear that a large number of best practices can be given a \textit{Fully automated} implementation by \textit{GreatAI}'s design, while an even larger number of them can be augmented by the library. This proves the feasibility of designing simple APIs using the techniques of Chapter \ref{chapter:design} for decreasing the complexity of correctly deploying AI services (\textbf{RQ2}).
\section{Interviews} \label{section:interviews}
-One of the takeaways of Chapter \ref{chapter:background} was that, for example, Seldon Core is useful for implementing or helping to implement many of the best practices. Regardless, it also has an initial threshold that must be surmounted before implementing even a single best practice. According to the adoption rate surveys, this presumably discourages a large portion of practitioners from using it or other similar frameworks. \textit{GreatAI} offers a different mix of features, the initial threshold is virtually non-existent: best practices can be immediately applied. But at the same time, the presented solution covers a smaller number of practices.
+One of the central takeaways of Section \ref{section:existing} was that, for example, Seldon Core is useful for implementing or helping to implement many of the best practices. Regardless, it also has an initial threshold that must be surmounted before implementing even a single one. According to the adoption rate surveys, this may discourage a large portion of practitioners from using it or other similar frameworks. The presented solution offers a different mix of features: the initial threshold is virtually non-existent; hence, best practices can be immediately applied. But at the same time, it only covers a more limited range of practices.
-The hypothesis is that the latter approach aligns better with the expectations of professionals. To verify this, a series of interviews were conducted with 10 industry practitioners of varying AI/ML and SE experience and backgrounds. In this Section, the question of generalisability (\textbf{RQ4}) is investigated using the interview methodology described in Section \ref{section:interview-setup}. The participants were gathered from the recommendations of my friends and colleagues. All of the final interviewees have had at least some expertise in both Data Science (with a median experience of 2.5 years) and Software Engineering (with a median experience of 2 years).
+The hypothesis is that the latter approach aligns better with the expectations of professionals. To verify this, a series of interviews were conducted with ten industry practitioners of varying AI/ML and SE experience and backgrounds. In this section, the question of generalisability (\textbf{RQ4}) is investigated using the interview methodology described in Section \ref{section:interview-setup}. The participants were gathered through the recommendations of my friends and colleagues. All of the final interviewees have had at least some expertise in both Data Science (with a median experience of 2.5 years) and Software Engineering (with a median experience of 2 years).
-\subsection{Best practices survey}
+\subsection{Best practices survey} \label{subsection:best-practices-survey-results}
-The practitioners were first asked to fill out a questionnaire about their latest AI/ML project, which involved deployment. This point-in-time survey (shown in Appendix \ref{appendix:practices}) served to measure a baseline for the deployment quality they are used to. Analysing the results show that the amount of software engineering experience has a moderately strong correlation ($r_{Pearson} = 0.67$ with $p = 0.0033$) with the overall number and extent of implemented deployment best practices. This is illustrated in Figure \ref{fig:adoption}. Interestingly, there is no similar statistically significant relationship when it comes to the amount of data science experience.
+The practitioners were first asked to fill out a questionnaire about their latest AI/ML project involving deployment. This point-in-time measurement (shown in Appendix \ref{appendix:practices}) served as a baseline for the deployment quality they are used to. Analysing the results show that the amount of software engineering experience has a moderately strong correlation ($r_{Pearson} = 0.67$ with $p = 0.0033$) with the overall number and extent of implemented deployment best practices. This is illustrated in Figure \ref{fig:adoption}. Interestingly but unsurprisingly, there is no similar statistically significant relationship regarding the amount of data science experience.
-The y-axis of Figure \ref{fig:adoption} is calculated by discarding the \textit{Not applicable} answers and projecting the 5-point Likert scale to a range from 0 to 1. The overall mean adoption rate/extent is just above 0.5, which equates to the \textit{Neither agree nor disagree} label. These data are in line with the findings of Serban et al. \cite{serban2020adoption}. Because the survey's 15 questions were compiled from Tables \ref{table:best-practices-1} and \ref{table:best-practices-2}, that means that when using \textit{GreatAI}, they are all implemented automatically. Consequently, the adoption rate/extent is doubled immediately: this is the added value of \textit{GreatAI}.
+The y-axis of Figure \ref{fig:adoption} is calculated by discarding the \textit{Not applicable} answers and projecting the 5-point Likert scale to a range from 0 to 1, which is subsequently averaged over all questions. The overall mean adoption rate/extent is just above 0.5, which equates to the \textit{Neither agree nor disagree} label. These data are in line with the findings of Serban et al. \cite{serban2020adoption}. Because the survey's 15 questions were compiled from Tables \ref{table:best-practices-1} and \ref{table:best-practices-2}, that means that when using \textit{GreatAI}, they are all implemented automatically. Consequently, the adoption rate/extent is doubled immediately: this is the added value of \textit{GreatAI}\footnote{As explained earlier, measuring quality as a function of best practice count would be dubious. Thus, the achieved magnitude of the doubling is not relevant; however, the direction of change is.}. Moreover, this provides further evidence for answering \textbf{RQ3} showing the extent of automatically implemented practices over \textit{non-GreatAI} deployments.
\begin{figure}
\centering
\includegraphics[width=0.7\linewidth]{figures/best-practices.png}
\captionsetup{width=.9\linewidth}
- \caption{Best practices adoption rate as a function of software engineering experience. The point sizes denote the practitioners' experience in Data Science (DS). The correlation between the axes is $r_{Pearson} = 0.67$ with $p = 0.0033$.}
+ \caption{Best practices adoption rate as a function of software engineering experience. The point sizes denote the practitioners' experience in Data Science (DS). The correlation between the axes is significant ($r_{Pearson} = 0.67$ with $p = 0.0033$).}
\label{fig:adoption}
\end{figure}
\subsection{Technology acceptance}
-Participants filled out a form (shown in Appendix \ref{appendix:questions}) after finishing their first deployment with \textit{GreatAI} to provide data for creating the technology acceptance model of the problem context. The survey contained 12 questions from 3 categories, which could be rated on a 7-point Likert scale. Following the methodology of \cite{cruz2019catalog}, the connections between the Perceived Utility (PU), Perceived Ease Of Use (PEOU), and the Intention to use (ITU) were analysed. Only two statistically significant ($P < 0.05$) correlations were uncovered: between PU and ITU ($r_{Pearson} = 0.81$ with $p = 0.0048$); and PEOU and ITU ($r_{Pearson} = 0.80$ with $p = 0.0068$). Learning from the findings of prior case studies, it is reasonable that both the perceived utility and the perceived ease of use play an equally important role in influencing potential clients' intention to use the deployment framework.
+Participants filled out a form (shown in Appendix \ref{appendix:questions}) after finishing their first deployment with \textit{GreatAI} to provide data for creating the technology acceptance model of the problem context. The survey contained 12 questions from 3 categories, which could be rated on a 7-point Likert scale. Following the methodology of \cite{cruz2019catalog}, the connections between the Perceived Utility (PU), Perceived Ease Of Use (PEOU), and Intention To Use (ITU) were analysed. Only two statistically significant ($P < 0.05$) correlations were uncovered: between PU and ITU ($r_{Pearson} = 0.81$ with $p = 0.0048$); and PEOU and ITU ($r_{Pearson} = 0.80$ with $p = 0.0068$). Learning from the findings of prior case studies, it is reasonable that both the \textit{perceived utility} and the \textit{perceived ease of use} play an equally important role in influencing professionals' \textit{intention to use} the deployment framework.
\begin{table}[H]
\centering
\captionsetup{width=.9\linewidth}
-\caption{Aggregated results of the TAM survey (sample size = 10) presented in Appendix \ref{appendix:questions}. The values are from a range between 1 and 7.}
+\caption{Aggregated results of the TAM survey (sample size = 10) presented in Appendix \ref{appendix:questions}. The input values range from 1 to 7.}
\label{table:tam}
{\renewcommand{\arraystretch}{1.2} % for the vertical padding
\begin{tabular}{|c|r|r|r|} \hline
- & \textbf{Perceived ease of use} & \textbf{Perceived utility} & \textbf{Intention to use} \\\hline
-\textbf{Median} & 5.750 & 6.375 & 6.250 \\\hline
-\textbf{Mean} & 5.450 & 6.125 & 5.950 \\\hline
-\textbf{Variance} & 1.080 & 0.740 & 1.747 \\\hline
+ & \textbf{Perceived ease of use} & \textbf{Perceived utility} & \textbf{Intention to use} \\\hline
+\textbf{Median} & 5.750 & 6.375 & 6.250 \\\hline
+\textbf{Mean} & 5.450 & 6.125 & 5.950 \\\hline
+\textbf{Standard deviation} & 1.039 & 0.850 & 1.322 \\\hline
\end{tabular}}
\end{table}
-The summary of the answers is presented in Table \ref{table:tam}. The value for ease of use lags behind the rest, but it is still quite high. It may be possible that PEOU would go up with further use. Nevertheless, the high perceived utility implies that \textit{GreatAI} shows its value early on. This validates the hypothesis that focusing on good API design is just as important as providing practical features.
+The summary of the answers is presented in Table \ref{table:tam}. The assessment of \textit{ease of use} lags behind the rest, but it is still quite high. It may be possible that PEOU would go up with further use. Nevertheless, the high \textit{perceived utility} implies that \textit{GreatAI} shows its value early on. This, combined with the correlations uncovered within the context's technology acceptance model, validates the hypothesis that focusing on good API design is just as necessary as providing practical features.
\subsection{Task solving \& exit interviews}
-To give qualitative depth to the previously presented quantitative results, it is time to discuss the main segment of the interviews. First, the volunteers were requested to skim through the library's documentation beforehand, and they were also given a short verbal overview during the one-on-one meetings. This was followed by having them solve a prepared deployment task\footnote{Available at \href{https://github.com/schmelczer/great-ai-interview-task}{github.com/schmelczer/great-ai-interview-task}.} concerning a similar lifecycle to that presented in the \textit{GreatAI} tutorials. The training part of the task had already been done, the participants only had to deploy a trained classification model.
+In order to give qualitative depth to the previously presented quantitative results, it is time to discuss the main segment of the interviews. The participants' backgrounds cover a vast and fascinating cross-section of industrial AI/ML: one of them researched market prediction models for the Hungarian State Treasury, but building an upcoming digital bank's core services, investigating companies' AI use as part of due diligence processes, intrusion detection from network packet traces, creating pose-recognition for people with disabilities, and predicting Sun activity at the European Space Agency are just some of the core activities they had been doing recently. Stemming from this diversity, these semi-structured interviews should provide valuable insights into the generalisability of \textit{GreatAI}.
-The participants' backgrounds cover a vast (and incredibly interesting) cross-section of industrial AI/ML use: one of them researched market prediction models for the Hungarian State Treasury, but building an upcoming digital bank's core services, investigating companies' AI use as part of due diligence processes, intrusion detection from network packet traces, creating pose-recognition for people with disabilities, and predicting Sun activity at the European Space Agency are just some of the core activities they have been doing recently. Stemming from this diversity, these semi-structured interviews should provide valuable insights into the generalisability of \textit{GreatAI}.
+First, the volunteers were asked to skim through the library's documentation beforehand, and they were also given a short verbal overview during the one-on-one sessions. This was followed by having them solve a prepared deployment task\footnote{Available at \href{https://github.com/schmelczer/great-ai-interview-task}{github.com/schmelczer/great-ai-interview-task}.}, which is a more straightforward instance of the AI development lifecycle presented in the \textit{GreatAI} tutorials. The training part of the task had already been done, and the participants only had to deploy a trained classifier. The interviews took approximately one and a half hours each.
-% The approach used to collect information from interviews and to report data
-% is based on the guidelines proposed by Halcomb et al. \cite{halcomb2006verbatim} It is a reflexive,
-% iterative process:
-% 1. Audio taping of the interview and concurrent note-taking.
-% 2. Reflective journaling immediately post-interview.
-% 3. Listening to the audiotape and revising memos.
-% 4. Triangulation.
-% 5. Data analysis.
+The guidelines proposed by Halcomb et al. \cite{halcomb2006verbatim} are followed for collecting information from interviews and reporting it. It is a reflexive, iterative process which starts by recording participants (with their permission) and concurrent note-taking. Reflective journaling is immediately done post-interview, which is subsequently extended and revised by listening to the recordings. Afterwards, the gathered information is interpreted by applying the methodology of thematic analysis \cite{alhojailan2012thematic}.
-% The first two authors conducted the interviews, which took approximately one
-% hour. We took notes during the interviews and we recorded the interviews with
-% the permission of the participants. An example of the notes taken with P09 is
-% shown in Fig. 4. This section outlines the main steps of our interview design.
-% The full details can be found in our corresponding case study protocol [14].
+Thematic analysis is an iterative qualitative investigation technique consisting of labelling, correlating, and structuring the central recurring topics raised during discussions. It has been successfully used in previous software engineering studies for extracting emergent patterns \cite{haakman2021ai,cruz2019catalog}. After labelling each aspect of the feedback, and two iterations of merging redundant or related topics, we end up with three overarching themes: \textit{Functionality}, \textit{API}, and \textit{Responsibility to adopt}. As we will soon see, these correspond to the \textit{perceived utility}, \textit{perceived ease of use}, and \textit{intetion to use} components of TAM moderately well.
-% Also, the process of memoing assisted
-% the researchers to capture their thoughts and interpretations of the interview
-% data [44]. The audio recordings could still be used to facilitate a review of
-% the interviewers’ performance, and assist interviewers to fill in blank spaces in
-% their field notes and check the relationship between the notes and the actual
-% responses [12].
+\paragraph{Functionality} The library's feature-set was complimented during most interviews, with one participant noting that, although the overall number of features is relatively small, most of them are utilised in most cases. Similarly, the \texttt{utilities} submodule was appreciated for helping greatly in the interview task, but non-NLP researchers noted its likely inadequacy for their area. Still, they would like to see ``bundle'' or ``toolbox''-style modules for their fields because it would save them from a lot of copy-pasting.
-% . Thematic analysis is a qualitative data analysis
-% method divided into four steps: 1) familiarization with data, 2) generating
-% initial labels, 3) reviewing themes, 4) defining and naming themes. This tech-
-% nique has been successfully used in previous software engineering studies to
-% extract patterns from software [9].
+The easy parallel feature extraction and large file handling support were highlighted multiple times for the reason that the particular interviewees had not encountered other libraries providing these features. Other concrete features, such as the searchable \textit{exceptions} column in the Dashboard's table and the \textit{feedback} mechanism, were also popular. One professional highlighted the latter for coercing users to consider a human-in-the-loop approach which is said to be often expected in modern systems.
-% This step was followed by reviewing themes – step 3 of thematic analysis –
-% in which we discussed each label and looked for other labels that could be
-% redundant. For example, we merged the labels Feasibility Study and Proof of
-% Concept together into a single theme. This step yielded 11 overarching themes
-% that we further detail in Section 4.
-% -----------------------------
+When reflecting on the framework from a bird's eye view, the generality and extendability of the API were emphasised. As explained by a senior engineer, this is mainly because once you commit to using it, it is important not to find yourself at a dead end for a specific use case forcing you to look for a different library. However, two participants also noted that for complete generality, \texttt{MATLAB} support would be necessary. Regarding non-functional features, private hosting (especially in banking and government), open-source auditability, and easy scaling (by means of an external database) were the top subjects of praise.
-### functionality (PU)
-+ You get a lot of features
-+ Debugging traces is nice, had some privacy concerns but was easy to find the solution in the docs -> disable\_logging=True
-+ it forces you to do Human in the loop
-+ Private cloud is very important in banking/treasury
-+ Scales well because doesn't depend on 1 DB
-+ Utilities good, hate writing feature extraction, Parallel feature extraction is fascinating, + Great for NLP, should work for other domains if utilities are implemented
-+ being extendable very important because if you start using it you get locked into it
-+ important to have support for all libs e.g. external matlab
-+ Largefile good, haven't heard of other solutions, versioning important -> awareness
+\paragraph{API} Regarding the surface through which clients interact with the library, the feedback is also positive but more nuanced. Many participants liked that the functions' behaviour is easy to guess from their names. The decorator syntax caused minor confusion but consulting the documentation solved the issues in all three cases. The CLI app \texttt{great-ai} was appreciated for having a close to trivial signature; the participant noted that she strives to use as few CLI commands as feasible. Surprisingly, even the practitioners with more data science background appreciated the Docker support. Nonetheless, one expert had a feature request for a configuration UI because his colleagues are used to handling MATLAB App Designer applications.
-### API (PEOU)
-- Do data scientists know what decorators are?
-- Parameter decorators on the function are bit weird but doesn't know how to do it better
-You cannot make an API simpler than the domain but you made it as simple as it could get - Magic save, where does it go? Transparency, balance between too automatic and simple
-+ Hates complicated CLI-s, great-ai is very simple
-+ Likes Docker, researchers know that
-- Won't use if it doesn't work out-of-the-box (this time, it worked, but focusin on the starter code is important)
-- Want clickable UI for setting the config - scientists (matlab deployment)
+The recurring theme of the discussions focused on the question of ``\textit{How simple is too simple?}''. The argument is that an API cannot be simpler than the domain in which it exists. More precisely, it can only be simpler at the cost of losing transparency. Let us take the example of saving models using \texttt{save\_model()}. If a project is set up correctly, it either has an initial \texttt{configure} call to the storage provider backend, or it has an appropriately named credentials file in the project's root, for instance, \texttt{s3.ini} or \texttt{mongo.ini}. Once set up, it is trivial to use as long as we do not divert from the happy path. However, if an issue arises, such as an upgrade or migration of MongoDB, debugging the application is non-trivial for its lack of transparency.
-### Whose responsibility is this? (ITU)
-- If I had to implement a REST API for a model, I'd do that instead of searching for a lib
-Easier to raise awareness if you have a solution
+In other words, we could say that the average (cognitive) complexity is low while the worst-case is as high --- if not higher --- than without using \texttt{save\_model()}. This proved to be somewhat controversial. However, ultimately, optimising the happy path of the AI/ML development lifecycle was deemed worthwhile by the participants in most cases. With the argument that the majority of the time spent during a project is spent on this path anyway. However, this raises the question of who exactly are the target users of \textit{GreatAI} and who will fix arising issues?
-research CD very poor and even industrial projects are sometimes one-man
-Cron job runs Matlab script that copies it to the prod env
-They used Colab + GitHub + W&B for the treasury -> Add one-click app, heroku
-- Already using AWS, sagemaker is preferred
+\paragraph{Responsibility to adopt} Let us first look at some insightful anecdotes that surfaced during the interviews. Especially in more research-oriented environments, production deployment pipelines can be of questionable robustness. This was demonstrated by one account of a simple single-machine deployment's pipeline: it is an interplay of \texttt{cron} jobs calling a series of shell and MATLAB scripts resembling a Rube Goldberg machine. But, connecting a couple of Google Colab accounts to a GitHub repository and Weights\&Biases to implement parallel model training can also be found in the industry.
-- Trying to appeal to both DS and SE was confusing at first, why training in tutorial if it's a deployment lib
-- Whose responsibility is using the lib? - What happens when you have to configure it?
-+ You need so many different experts for a single project, too many, SE is often missing
-- AI is mostly used in academy, they have no reason to do good deployment or deployment at all
-DS, domain experts don't care about best-practices, End results should look nice, no one cares about behind the scenes
-You have to give a value proposition: low maintenance, low cost, better quality
-At one company, they had 0 DS people for 3 years, High-level solution can substitute missing professionals imo
-Shouldn't care about DS but instead decision-makers because they chose not to hire SE
- + You can have fewer SE-s instead of 0 but still more than 0 and they're effective with great-ai
+These, when combined with the fact that various research companies were mentioned that for multiple years used to or still have an R\&D department consisting solely of data scientists. In one extreme case, the staff was described as more than 30 data scientists and 0 other technical employees. In such a setup, it is unreasonable to expect even professionals to have the capabilities and focus to set up the required foundation for handling all best practices. All but one interviewee verified this assumption. They also referred to their previous projects, which usually required many researchers and experts from various fields, and too often, software engineers are not prioritised to be included.
+
+Doing software engineering without software engineers is difficult. \textit{GreatAI} is not a viable replacement for any well-trained expert, though it is still better than nothing. During the interviews, we realised that the likely underlying reason for not employing AI engineers or software engineers as part of AI/ML projects is a lack of awareness. This was theorised by some and demonstrated by six participants who had, even though followed some, not explicitly sought out AI deployment best practices. Thus, raising awareness --- especially by presenting a value proposition, e.g. lower maintenance costs, better long-term quality --- might be crucial for generally improving AI deployments. Verifying this hypothesis could be a worthwhile direction for future research.
+
+During the larger discussions, \textit{GreatAI} was deemed appropriate for awareness raising since it showcases how even a simple library is able to implement a lot of best practices. Additionally, it was noted that it could also be considered for one-person projects where --- by definition --- it is admissible to have no SE expert on the ``team''. To further help such cases, integrating a one-click Heroku\footnote{\href{https://www.heroku.com/}{heroku.com}} app deployment was also recommended to simplify the entire second half of the lifecycle.
+
+\subsection{Discussion of interviews}
+
+My overall takeaway from this is that most features were well-received, and the high mean value of \textit{perceived utility} is credible. The criticism of being NLP-centric is also justified: the initial scope of the proof-of-principle framework was limited to this domain. Nonetheless, learning the experts' opinion that they wish to have a similarly specific solution to their problem contexts is reassuring because it proves that the API is not only generalisable but is expected to be generalised. At the same time, it is crucial to admit that no one-size-fits-all solution can exist for such a diverse domain. Therefore, allowing customizability and easy extension of the system must remain central design questions.
+
+Regarding the API's level of abstraction, I have to agree with the experts that the problem of deployment cannot be ``magically'' solved by a trivial API. However, solving deployment problems can be streamlined, at least in simpler cases. While the complex ones can be left to the professionals with relevant knowledge. This parallels the AI-libraries that have inspired \textit{GreatAI}, for instance, HuggingFace's \texttt{transformers} streamlines fine-tuning and applying SOTA models, but it does not provide any facilities to help you create the next SOTA architecture because that is a vastly more complex task that most users do not wish to tackle.
+
+In order to reach its goal of improving best practice adoption, \textit{GreatAI} can help raise awareness by presenting a verifiable value proposition, i.e. a couple of lines of code can already result in more maintainable, robust, high-quality deployments. This might prompt users or technical decision-makers to invest more in software engineering in AI/ML projects. Additionally, it can help the effectiveness of AI/software engineers by handling the grunt work of implementing some best practices and therefore leave them with more resources to focus on the complex and creative aspects of \textit{GREAT} deployments.
+
+In summary, the answer to \textit{How suitable is the design of GreatAI for helping to apply best practices in other contexts?} (\textbf{RQ4}) is --- unsurprisingly --- subjective. Combining the high value of \textit{intention to use} from Table \ref{table:tam}, the generally positive feedback regarding the library's added value, and numerous feature requests for fine-tuning it to specific needs, we can conclude that there is some chance of suitability for generalisability. The existence of this potential is already exciting and presents an opportunity for experimenting with building on the design of \textit{GreatAI}.
\subsection{Threats to validity}
+Two potential threats to the validity of the experiments and their results are identified. Firstly, the claimed utility of the framework derived in Subsection \ref{subsection:best-practices-survey-results} does not take into account the practical significance of the implemented features and, therefore, may be subject to bias. However, the \textit{perceived utility} evaluations indicate that the participating engineers and scientists identify practical value in the features of \textit{GreatAI}. Nevertheless, in the future, we intend to extend the range of implemented best practices, which would in turn, give higher confidence about the achievable quantitative improvement through using the library.
+
+Secondly, the survey answers and, in general, the interviewees may be subject to bias. The small sample size of practitioners can reasonably lead to some groups being over- or under-represented. The presence of selection bias is also plausible. These could be mitigated by gathering more data in future research. Coming from the exploratory nature of this analysis, many insights could be gained from the collected data. However, for confidently generalising the results, more data are needed.
+
\section{Future work}
-The primary purpose of \textit{GreatAI} was to serve as a proxy through which its design decisions could be tested and evaluated in their practical context. For this reason, its design aimed to be a proof-of-principle for validating hypotheses and answering research questions. After successfully doing that, it has been turned into a practical software library suitable for production-use\footnote{\href{https://pypi.org/project/great-ai/}{pypi.org/project/great-ai}}. Although it has already proved its utility, it has also shown that extending its functionality would be worthwhile. Therefore, a number of potential improvements to \textit{GreatAI} are presented below.
+The primary purpose of the library was to serve as a proxy through which its design decisions could be tested and evaluated in their practical context. For this reason, its design aimed to be a proof-of-principle for validating hypotheses and answering research questions. After successfully doing that, it has been turned into a practical software library suitable for production-use\footnote{\href{https://pypi.org/project/great-ai/}{pypi.org/project/great-ai}}. Although it has already proved its utility, it has also shown that extending its functionality would be worthwhile. Therefore, a number of potential improvements to \textit{GreatAI} are presented below primarily from the needs arisen during the exit interviews.
-\subsection{More data science}
+\subsection{More AI/ML fields}
-The cases presented in Chapter \ref{chapter:case} revolved around NLP. This, unsurprisingly, heavily influenced the design process. The two most notable effects can be found in the REST API's \texttt{/predict} endpoint and some \texttt{utilities} functions. The former is streamlined to accept JSON-compatible data while the latter gives robust feature extraction support for only textual inputs. Supporting the easy, direct upload of larger non-JSON files --- e.g. by saving them to S3 and showing a preview for them on the Dashboard's trace table --- and extending \texttt{utilities} to handle multimedia formats should be sufficient for widely extending the scope of applicability of \textit{GreatAI}.
+The cases presented in Chapter \ref{chapter:case} revolved around NLP. This, of course, heavily influenced the design process. The two most notable effects can be found in the REST API's \texttt{/predict} endpoint and some \texttt{utilities} functions. The former is streamlined to accept JSON-compatible data, while the latter gives robust feature extraction support for only textual input. Supporting the easy, direct upload of larger non-JSON files --- e.g. by saving them to S3 and showing a preview for them on the Dashboard's trace table --- and extending \texttt{utilities} to handle multimedia formats should be sufficient for widely expanding the scope of applicability of \textit{GreatAI}.
-\subsection{More software engineering}
+\subsection{More best practices}
-In order to greatly simplify its API, each \textit{GreatAI} Trace is a single document with a well-defined, multi-level schema that clients can also extend by calling \texttt{log\_metric}. MongoDB provides a convenient (and popular) method for persisting such documents, however, if there is some existing database in the environment, storing Traces in that can be favourable. \href{https://www.postgresql.org/}{PostgreSQL} is a popular choice and it also features good JSON document support. Hence, introducing first-class integration for PostgreSQL could benefit some clients.
+In order to greatly simplify its API, each \textit{GreatAI} Trace is a single document with a well-defined, multi-level schema that clients can also extend by calling \texttt{log\_metric}. MongoDB provides a convenient (and popular) method for persisting such documents; however, if there is some existing database in the environment, storing Traces in that can be favourable. \href{https://www.postgresql.org/}{PostgreSQL} is a popular choice, and it also features good JSON document support. Hence, introducing first-class integration for PostgreSQL could benefit some clients.
As described in Designing Data-intensive Applications \cite{kleppmann2017designing}, services can fall into three broad categories: online systems, batch processing, and stream processing (near-teal-time systems). As of yet, \textit{GreatAI} only provides streamlined support for the first two. Thus, developer experience could be improved by providing simple, direct integration with popular message queues/protocols, such as \href{https://kafka.apache.org/}{Apache Kafka} \cite{kreps2011kafka}, \href{https://aws.amazon.com/sqs/}{AWS SQS} \cite{garfinkel2007evaluation}, or \href{https://www.amqp.org/}{AMQP} \cite{vinoski2006advanced}.
-Some metrics of \textit{GreatAI}, such as the cache statistics, versions, and derived data from traces can be already conveniently queried from its REST API. Nevertheless, adding support for the de facto standard metric gathering tool \href{https://prometheus.io/}{Prometheus} could save the library's users from one more integration step.
+Some metrics of \textit{GreatAI}, such as the cache statistics, versions, and derived data from traces, can already be conveniently queried from its REST API. Nevertheless, adding support for the de facto standard metric gathering tool \href{https://prometheus.io/}{Prometheus} could save the library's users from one more integration step.
-The common theme among the above-mentioned opportunities is that they could be reasonably well implemented without any user input, making them in line with the library's philosophy. Of course, the open-source nature of \textit{GreatAI} also allows anyone to already provide support for a wide range of integrations. Additionally, the scope could be also reasonably extended, i.e. more practices could be covered by including more criteria next to the GREAT ones.
+The common theme among the opportunities mentioned above is that they could be reasonably well implemented without any user input, which aligns with the library's philosophy. Of course, the open-source nature of \textit{GreatAI} also allows anyone already to provide support for a wide range of integrations. Additionally, the scope could be reasonably extended, i.e. more practices could also be incorporated into the scope by including more criteria next to the \textit{GREAT} ones.
diff --git a/thesis/chapters/7_conclusion.tex b/thesis/chapters/7_conclusion.tex
index bf9b628..64fa820 100644
--- a/thesis/chapters/7_conclusion.tex
+++ b/thesis/chapters/7_conclusion.tex
@@ -1,7 +1,15 @@
-\chapter{Conclusion} \label{chapter:conclusion}
+\chapter{Conclusion} \label{chapter:conclusion}
-todo
+Concerned by the asymmetry between the industry's adoption of accessible AI/ML-libraries and existing solutions for their robust deployment, we investigated this phenomenon's causes and potential resolution. When looking at various recent case studies, a recurring theme was revealed: \textit{transitioning} from prototype to production-ready AI/ML deployment is a source of adversity for small and large enterprises alike. Even though several frameworks and platforms exist for facilitating this step, surveys on the execution of best practices continue to expose the industry's shortcomings. This signals that existing libraries are underutilised, which may lead to poor AI deployments that underperform or develop issues that go unnoticed and might inflict societal harm.
-\textit{GreatAI} may have the potential to bridge the gap between data science and software engineering. Stemming from the bidirectional nature of bridges, we can look at the framework from two perspectives: for professionals closer to the field of data science, it provides an automatic scaffolding of software facilities that are required for deploying, monitoring, and iterating on their models. For software engineers, it highlights the necessary steps required for robust and improvable deployments --- while, at the same time, it saves them from the menial work of manually implementing these constructs. While most importantly, it proves that increasing the adoption rate of AI/ML deployment best practices is viable by designing narrower and deeper APIs.
+It was hypothesised that presenting a library which implements best practices and is also optimised for ease of adoption could help increase the overall quality of industrial AI/ML deployments. To test this, a framework was designed and implemented based on the principles of cognitive science and the prior art of software design. The design was subsequently tested and refined in an iterative process. First, a model was developed and deployed for classifying the domains of academic publications. Then, a SciBERT model was fine-tuned and deployed for generating the technology-transfer summaries of the same publications. \textit{GreatAI} had been proven helpful; therefore, after feeding back the insights gained into its design, it was turned into an open-source library. Furthermore, \textit{GreatAI} has been successfully integrated into every production deployment of ScoutinScience since then and recieves thousands of monthly downloads.
-Good deployments benefit all of us. Henceforth, continued research into the means of good deployments remains crucial. However, next to that --- as the presented results show --- better deployments can also be achieved by facilitating the \textit{transition} step of the AI lifecycle. Having automated implementations, even if for just more straightforward best practices, leaves professionals more time to tackle other deployment challenges and fewer opportunities to miss crucial steps. Overall, resulting in more implemented practices, hence, robust and trustworthy production software.
+During the refinement of the framework, six previously unaddressed AI/ML deployment best practices were identified. Including these, the framework fully implements 17 best practices while it provides support for another 16. The value provided by implementing or helping to implement these practices was validated through interviews with ten industry professionals from various fields.
+
+The interview participants completed two questionnaires, the results of one of which indicated that using \textit{GreatAI} in an example task increased the number of implemented best practices by 49\% compared with their latest project. The technology acceptance model was also calculated for the context; a significantly strong correlation was measured between the perceived ease of use, the perceived utility and the intention to use dimensions. Overall, proving that ease of use is just as important as core functionality when it comes to adopting AI deployment frameworks.
+
+The open-ended exit interviews revealed that value can be derived from the library even in its current form and that the API's design has the opportunity to generalise to other fields of industrial AI/ML applications. However, they also highlighted that adoption issues do not necessarily come from a lack of willingness but a lack of awareness. Even if the returns achievable from good deployments are well worth the investment. Nevertheless, this value proposition needs to be conveyed and proved to data science professionals and technical decision-makers; and \textit{GreatAI} might just be the ideal candidate for that.
+
+\textit{GreatAI} may have the potential to bridge the gap between data science and software engineering. Stemming from the bidirectional nature of bridges, we can look at the framework from two perspectives: for professionals closer to the field of data science, it provides an automatic scaffolding of software facilities that are required for deploying, monitoring, and iterating on their models. For software engineers, it highlights the necessary steps required for robust and improvable deployments. At the same time, it also saves them from the menial work of manually implementing these constructs. While most importantly, it proves that increasing the adoption rate of AI/ML deployment best practices is feasible by designing narrower and deeper APIs.
+
+Good deployments benefit all of us. Accordingly, continued research into the means of good deployments remains crucial. However, next to that --- as the presented results have shown --- better deployments can also be achieved by facilitating the \textit{transition} step of the AI lifecycle with a focus on adoptability. Having automated implementations, even if for just the straightforward best practices, leaves professionals additional time to tackle the more complex deployment challenges and fewer opportunities to miss critical steps. Overall, resulting in more robust, end-to-end automated, and trustworthy AI deployments.
diff --git a/thesis/comments.txt b/thesis/comments.txt
index 5f0d045..a528696 100644
--- a/thesis/comments.txt
+++ b/thesis/comments.txt
@@ -1,7 +1,176 @@
-% I use a toy example when quickly experimenting, it's important not to overfit on it ( moving it into the library would result in a online for it, so I have to consciously avoid that), but having a very simple
+Thesis notes
-% Argumetn/parameter names were confusing
-% offlinemode -> cacheonly mode
-% Should the order of the decorators matter? all except in one case, they're written in a way that the order doesn't matter even with the original semantics of decorators. In that one case, it cannot be written in that way. Instead of correcting a user's error, there's a mechanism looking for this error and the user is notified. Guessing the unspecified is cool, but correcting the wrong is not
+Should the order of the decorators matter? all except in one case, they're written in a way that the order doesn't matter even with the original semantics of decorators. In that one case, it cannot be written in that way. Instead of correcting a user's error, there's a mechanism looking for this error and the user is notified. Guessing the unspecified is cool, but correcting the wrong is not
+✅ hot-reload
+✅ Extract doc comment from function with markdown
+✅ Evaluate endpoint
+✅ body instead of query
+✅ automatically find parameters
+✅ Generic return types
+✅ Data engineer notebook, ds notebook, deployment script
+✅ Nice error handling
+✅ notebook support
+✅ Evaluation result return type that contains explanation - explanation field
+✅ largefiles mongo backend
+✅ Fix endpoints
+✅ Bug: should recreate table
+✅ Mongo, Create index for each encountered field - async
+✅ Save test/train data - tags and ground truth classifier?
+✅ Handle multiple great ai instances
+✅ create_shadow_deployment -> traceId, evaluationId
+
+Show model accuracy statistics
+Test entry point function -> with expected error rate
+
+Show data distribution - buttons in header?
+
+Cannot be installed -> save model card, https://github.com/tensorflow/model-card-toolkit
+
+Cannot use google-research/robustness_metrics Only works for TF
+
+Why do I have a complex example, it's supposed to be a simple library
+Argumetn/parameter names were confusing
+
+For example: large file is easy to replace, the decisions are found by the best practices table and highlighted on the dashboard
+
+During development, I wanted to check out which types of request fail -> log errors in traces
+Even production systems are not perfect, saving and letting the users filter on the errors is useful. e.g. they can correlate it with the input
+
+Should the order of the decorators matter? all except in one case, they're written in a way that the order doesn't matter even with the original semantics of decorators. In that one case, it cannot be written in that way. Instead of correcting a user's error, there's a mechanism looking for this error and the user is notified. Guessing the unspecified is cool, but correcting the wrong is not
+
+Users like sonar checks, ci/cd, docker files, makes the project seem more trustworthy, also provides integration for them
+
+Leslie Lamport: problems are difficult to find at a research h table, they come from practice
+
+%matplotlib inline is called automatically on first draw, very confusing as it resets the rcParams, you have to set them twice, like come on
+
+ Have to explicitly write version="latest" to signify that it can change any time someone uploads a new model
+
+offline_mode -> cache_only_mode
+
+--------------------------------------------
+
+Design science methodology for information systems and software engineering \cite{wieringa2014design}
+
+design science research are design problems through its research method, the design cycle
+
+Design science is the design and investigation of artifacts in context
+
+Help a class of stakeholders
+
+e, we outline a research agenda for AI engineering research to help the research community structure and conceptualize the problem space.
+]. In addition to this, model deployment is a highly underestimated area [3].
+
+
+Unfortunately, our research [3]–[5] shows that the transition from prototype to production-quality deployment of ML models proves to be challenging for many companies.
+
+AI engineering (which we define as an extension of Software Engineering with new processes and technologies needed for development and evolution of AI systems
+a set of 16 primary cases as the foundation for the challenges we identify and the research agenda we outline.
+
+cases representing startups as well as large multinational companies in domains such as e.g. real estate, weather forecasting, fraud detection, sentiment analysis and failure prediction
+
+we outline a research agenda for AI engineering research to help the research community structure and conceptualize the problem space
+
+significant additional functionality is required to ensure that the ML/DL model can operate in a reliable and predictable fashion with proper engineering of data pipelines, monitoring and logging, etc. [2], [11]. T
+
+Instead, we provide an overview in figure 2 and present a categorization of the identified problems in four strategic focus areas, relating to the typical phases of a ML project. These four areas are the following:
+
+
+AI Lifecycle Models Need To Be Revised \cite{haakman2021ai}
+
+Fintech - ING
+
+We have found that the following stages have been overlooked by previous lifecycle models: data collection, feasibility study, documentation, model monitoring, and model risk assessment.
+more focus is needed on the entire lifecycle. In particular, regardless of the existing development tools for Machine Learning, we observe that they are still not meeting the particularities of this field.
+
+Cross-Industry Standard Process for Data Mining (CRISP-DM) [39] and the Team Data Science Process (TDSP)
+\cite{wirth2000crisp}
+https://docs.microsoft.com/en-us/azure/architecture/data-science-process/overview
+
+What if you just use huggingface?
+
+"it is hard to isolate two different machine learning models that operate in the same systemA – often they ought to be developed and training together"
+
+For example, the team of P08 keeps track of an experiment log using a spreadsheet, in which the training set, validation set, model, and preprocessing steps are specified for each version. This approach for versioning is preferred over solutions like MLFlow7 for the sake of simplicity
+
+Teams resort to self-developed or highly-customized dashboard platforms to monitor the models (P15, P16)
+
+Researchers could focus on solving the reported challenges in the Machine Learning lifecycle with additional tool support and reveal challenges of the ML lifecycle in other domains by extending the case study to more organizations and different types of industries
+Our study shows that, despite the increasing trend on improving the state-of-the-art model training techniques, there is a research gap on the challenges of developing real-world machine learning systems. F
+
+It is also necessary to create holistic monitoring solutions that can scale to different models in an organization
+
+
+
+AI Deployment Architecture: Multi-Case Study for Key Factor Identification
+According to [12] and [13], developing, deploying and maintaining complex commercial ML-based system is a challenging task. Most ML-based systems have strict latency requirements at inference stage [14]. Training-serving skew also results in sub-optimal model performance [15]. For the realistic implementation of ML, there is a need to consider and adapt well established SE practices which have been ignored or had a very narrow focus in ML literature [16] [17].
+
+Software Engineering for Machine Learning: A Case Study
+
+MicrosoftE
+
+Automation is a vital cross-cutting concern
+
+Automating tests is as important in machine learning as it is in software engineering; teams create carefully put-together test sets that capture what their models should do. However, it is important that a human remains in the loop. One respondent said, “we spot check and have a human look at the errors to see why this particular category is not doing well, and then hypothesize to figure out problem source.”
+
+In addition, respondents with low experience rank challenges with integrating AI into larger systems higher than those with medium or high experience.
+
+. Software engineers prefer to design and build systems which are elegant, abstract, modular, and simple. By contrast, the data used in machine learning are voluminous, context-specific, heterogeneous, and often complex to describe. These differences result in difficult problems when ML models are integrated into software systems at scale.
+
+---
+
+[3] AI components can be entangled in complex ways
+. Thus, even if separate teams built each model, they would have to collaborate closely in order to properly train or maintain the full system. This phenomenon (also referred to as component entanglement) can lead to non-monotonic error propagation, meaning that improvements in one part of the system might decrease the overall system quality because the rest of the system is not tuned to the latest improvements.
+
+Ethics guidelines for trustworthy AI
+
+https://digital-strategy.ec.europa.eu/en/library/ethics-guidelines-trustworthy-ai
+
+> (3) robust - both from a technical perspective while taking into account its social environment
+
+7 key requirements
+Human agency and oversight:
+Technical Robustness and safety:
+Transparency
+Accountability
+
+Understanding Development Process of Machine Learning Systems: Challenges and Solutions \cite{de2019understanding}
+
+Given that several ML system development companies are either startups or small companies with few developers, it is of utmost importance to understand the needs and challenges of developers working in these small organizations.
+
+ns. However, there is a gap in understanding how professionals develop ML systems in small and local companies.
+
+
+Versioning for End-to-End Machine Learning Pipelines \cite{van2017versioning}
+Highlights the importance of schema versioning in an environment of rapidly changing models and transformations
+
+Adoption and Effects of Software Engineering Best FinaPractices in Machine Learning \cite{serban2020adoption}
+aim: determine the state of the art in how teams develop, deploy and maintain software with ML components.
+
+t traditional software engineering practices tend to have lower adoption than ML specific practices
+
+distilled a set of 29 engineering best practices
+
+For example, our results suggest that traceability would benefit most from increased adoption of practice 25, the logging of production predictions with model versions and input data.
+
+Practices for Engineering Trustworthy Machine Learning Applications \cite{serban2021practices}
+
+the negative impact that improper use of ML can have on users and society is now also widely recognised
+
+In total, we identified 14 new practices, and used them to complement an existing catalogue of ML engineering practices.
+
+Well-intentioned but improper development of ML components can cause unintentional harm [2].
+
+trustworthy ML is relatively low.
+
+clearly reflect a desire for ML components to be lawful, ethical and robust [1]. H
+
+In this paper, we aim to bridge the gap between guidelines from policy makers and operational practices for developers and their immediate collaborators.
+
+
+However, none of these lines of work tackle issues related to the negative impact that improper use of ML has on society
+
+
+We also believe that the adoption of trustworthiness-specific and general ML engineering practices is interconnected; for instance, the practice of continuous integration [6] can make the practices for bias testing more effective.
diff --git a/thesis/main.pdf b/thesis/main.pdf
index eda4194..7ceaf0e 100644
Binary files a/thesis/main.pdf and b/thesis/main.pdf differ
diff --git a/thesis/ref.bib b/thesis/ref.bib
index 52eda45..cea77bc 100644
--- a/thesis/ref.bib
+++ b/thesis/ref.bib
@@ -666,17 +666,6 @@
publisher={SAGE Publications Sage CA: Los Angeles, CA}
}
-@article{cruz2019catalog,
- title={Catalog of energy patterns for mobile applications},
- author={Cruz, Luis and Abreu, Rui},
- journal={Empirical Software Engineering},
- volume={24},
- number={4},
- pages={2209--2235},
- year={2019},
- publisher={Springer}
-}
-
@article{leite2019survey,
title={A survey of DevOps concepts and challenges},
author={Leite, Leonardo and Rocha, Carla and Kon, Fabio and Milojicic, Dejan and Meirelles, Paulo},
@@ -858,3 +847,24 @@ numpages = {3}
year={1995},
publisher={Pearson Deutschland GmbH}
}
+
+@article{alhojailan2012thematic,
+ title={Thematic analysis: A critical review of its process and evaluation},
+ author={Alhojailan, Mohammed Ibrahim},
+ journal={West east journal of social sciences},
+ volume={1},
+ number={1},
+ pages={39--47},
+ year={2012}
+}
+
+@article{cruz2019catalog,
+ title={Catalog of energy patterns for mobile applications},
+ author={Cruz, Luis and Abreu, Rui},
+ journal={Empirical Software Engineering},
+ volume={24},
+ number={4},
+ pages={2209--2235},
+ year={2019},
+ publisher={Springer}
+}
diff --git a/tutorial/deploy/index.html b/tutorial/deploy/index.html
index 377e833..8fd6716 100644
--- a/tutorial/deploy/index.html
+++ b/tutorial/deploy/index.html
@@ -1076,6 +1076,7 @@ span.linenos.special { color: #000000; background-color: #ffffc0; padding-left:
.highlight-ipynb .m { color: var(--jp-mirror-editor-number-color) } /* Literal.Number */
.highlight-ipynb .s { color: var(--jp-mirror-editor-string-color) } /* Literal.String */
.highlight-ipynb .ow { color: var(--jp-mirror-editor-operator-color); font-weight: bold } /* Operator.Word */
+.highlight-ipynb .pm { color: var(--jp-mirror-editor-punctuation-color) } /* Punctuation.Marker */
.highlight-ipynb .w { color: var(--jp-mirror-editor-variable-color) } /* Text.Whitespace */
.highlight-ipynb .mb { color: var(--jp-mirror-editor-number-color) } /* Literal.Number.Bin */
.highlight-ipynb .mf { color: var(--jp-mirror-editor-number-color) } /* Literal.Number.Float */
diff --git a/tutorial/train/index.html b/tutorial/train/index.html
index 22e0758..25aae82 100644
--- a/tutorial/train/index.html
+++ b/tutorial/train/index.html
@@ -1076,6 +1076,7 @@ span.linenos.special { color: #000000; background-color: #ffffc0; padding-left:
.highlight-ipynb .m { color: var(--jp-mirror-editor-number-color) } /* Literal.Number */
.highlight-ipynb .s { color: var(--jp-mirror-editor-string-color) } /* Literal.String */
.highlight-ipynb .ow { color: var(--jp-mirror-editor-operator-color); font-weight: bold } /* Operator.Word */
+.highlight-ipynb .pm { color: var(--jp-mirror-editor-punctuation-color) } /* Punctuation.Marker */
.highlight-ipynb .w { color: var(--jp-mirror-editor-variable-color) } /* Text.Whitespace */
.highlight-ipynb .mb { color: var(--jp-mirror-editor-number-color) } /* Literal.Number.Bin */
.highlight-ipynb .mf { color: var(--jp-mirror-editor-number-color) } /* Literal.Number.Float */