great-ai/docs/thesis/ref.bib

591 lines
20 KiB
BibTeX
Raw Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

@article{haakman2021ai,
title={AI lifecycle models need to be revised},
author={Haakman, Mark and Cruz, Lu{\'\i}s and Huijgens, Hennie and van Deursen, Arie},
journal={Empirical Software Engineering},
volume={26},
number={5},
pages={1--29},
year={2021},
publisher={Springer}
}
@inproceedings{amershi2019software,
title={Software engineering for machine learning: A case study},
author={Amershi, Saleema and Begel, Andrew and Bird, Christian and DeLine, Robert and Gall, Harald and Kamar, Ece and Nagappan, Nachiappan and Nushi, Besmira and Zimmermann, Thomas},
booktitle={2019 IEEE/ACM 41st International Conference on Software Engineering: Software Engineering in Practice (ICSE-SEIP)},
pages={291--300},
year={2019},
organization={IEEE}
}
@book{wieringa2014design,
title={Design science methodology for information systems and software engineering},
author={Wieringa, Roel J},
year={2014},
publisher={Springer}
}
@inproceedings{serban2020adoption,
title={Adoption and effects of software engineering best practices in machine learning},
author={Serban, Alex and van der Blom, Koen and Hoos, Holger and Visser, Joost},
booktitle={Proceedings of the 14th ACM/IEEE International Symposium on Empirical Software Engineering and Measurement (ESEM)},
pages={1--12},
year={2020}
}
@inproceedings{de2019understanding,
title={Understanding development process of machine learning systems: Challenges and solutions},
author={de Souza Nascimento, Elizamary and Ahmed, Iftekhar and Oliveira, Edson and Palheta, M{\'a}rcio Piedade and Steinmacher, Igor and Conte, Tayana},
booktitle={2019 ACM/IEEE International Symposium on Empirical Software Engineering and Measurement (ESEM)},
pages={1--6},
year={2019},
organization={IEEE}
}
@inproceedings{serban2021practices,
title={Practices for engineering trustworthy machine learning applications},
author={Serban, Alex and van der Blom, Koen and Hoos, Holger and Visser, Joost},
booktitle={2021 IEEE/ACM 1st Workshop on AI Engineering-Software Engineering for AI (WAIN)},
pages={97--100},
year={2021},
organization={IEEE}
}
@article{sculley2015hidden,
title={Hidden technical debt in machine learning systems},
author={Sculley, David and Holt, Gary and Golovin, Daniel and Davydov, Eugene and Phillips, Todd and Ebner, Dietmar and Chaudhary, Vinay and Young, Michael and Crespo, Jean-Francois and Dennison, Dan},
journal={Advances in neural information processing systems},
volume={28},
year={2015}
}
@book{ousterhout2018philosophy,
title={A philosophy of software design},
author={Ousterhout, John K},
volume={98},
year={2018},
publisher={Yaknyam Press Palo Alto}
}
@book{hermans2021programmer,
title={The Programmer's Brain: What every programmer needs to know about cognition},
author={Hermans, Felienne},
year={2021},
publisher={Simon and Schuster}
}
@inproceedings{van2017versioning,
title={Versioning for end-to-end machine learning pipelines},
author={Van Der Weide, Tom and Papadopoulos, Dimitris and Smirnov, Oleg and Zielinski, Michal and Van Kasteren, Tim},
booktitle={Proceedings of the 1st Workshop on Data Management for End-to-End Machine Learning},
pages={1--9},
year={2017}
}
@inproceedings{li2017scaling,
title={Scaling machine learning as a service},
author={Li, Li Erran and Chen, Eric and Hermann, Jeremy and Zhang, Pusheng and Wang, Luming},
booktitle={International Conference on Predictive Applications and APIs},
pages={14--29},
year={2017},
organization={PMLR}
}
@inproceedings{wirth2000crisp,
title={CRISP-DM: Towards a standard process model for data mining},
author={Wirth, R{\"u}diger and Hipp, Jochen},
booktitle={Proceedings of the 4th international conference on the practical applications of knowledge discovery and data mining},
volume={1},
pages={29--40},
year={2000},
organization={Manchester}
}
@article{wirtz2019artificial,
title={Artificial intelligence and the public sector—applications and challenges},
author={Wirtz, Bernd W and Weyerer, Jan C and Geyer, Carolin},
journal={International Journal of Public Administration},
volume={42},
number={7},
pages={596--615},
year={2019},
publisher={Taylor \& Francis}
}
@inproceedings{akbik2019flair,
title={FLAIR: An easy-to-use framework for state-of-the-art NLP},
author={Akbik, Alan and Bergmann, Tanja and Blythe, Duncan and Rasul, Kashif and Schweter, Stefan and Vollgraf, Roland},
booktitle={Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics (Demonstrations)},
pages={54--59},
year={2019}
}
@article{wolf2019huggingface,
title={Huggingface's transformers: State-of-the-art natural language processing},
author={Wolf, Thomas and Debut, Lysandre and Sanh, Victor and Chaumond, Julien and Delangue, Clement and Moi, Anthony and Cistac, Pierric and Rault, Tim and Louf, R{\'e}mi and Funtowicz, Morgan and others},
journal={arXiv preprint arXiv:1910.03771},
year={2019}
}
@article{devlin2018bert,
title={Bert: Pre-training of deep bidirectional transformers for language understanding},
author={Devlin, Jacob and Chang, Ming-Wei and Lee, Kenton and Toutanova, Kristina},
journal={arXiv preprint arXiv:1810.04805},
year={2018}
}
@book{srinivasa2018natural,
title={Natural Language Processing and Computational Linguistics: A practical guide to text analysis with Python, Gensim, spaCy, and Keras},
author={Srinivasa-Desikan, Bhargav},
year={2018},
publisher={Packt Publishing Ltd}
}
@article{vrehuuvrek2011gensim,
title={Gensim—statistical semantics in python},
author={Rehrek, Radim and Sojka, Petr and others},
journal={Retrieved from genism. org},
year={2011}
}
@article{pedregosa2011scikit,
title={Scikit-learn: Machine learning in Python},
author={Pedregosa, Fabian and Varoquaux, Ga{\"e}l and Gramfort, Alexandre and Michel, Vincent and Thirion, Bertrand and Grisel, Olivier and Blondel, Mathieu and Prettenhofer, Peter and Weiss, Ron and Dubourg, Vincent and others},
journal={the Journal of machine Learning research},
volume={12},
pages={2825--2830},
year={2011},
publisher={JMLR. org}
}
@article{sun2019summarizing,
title={Summarizing CPU and GPU design trends with product data},
author={Sun, Yifan and Agostini, Nicolas Bohm and Dong, Shi and Kaeli, David},
journal={arXiv preprint arXiv:1911.11313},
year={2019}
}
@article{jordan2015machine,
title={Machine learning: Trends, perspectives, and prospects},
author={Jordan, Michael I and Mitchell, Tom M},
journal={Science},
volume={349},
number={6245},
pages={255--260},
year={2015},
publisher={American Association for the Advancement of Science}
}
@book{o2016weapons,
title={Weapons of math destruction: How big data increases inequality and threatens democracy},
author={O'neil, Cathy},
year={2016},
publisher={Broadway Books}
}
@inproceedings{wang2020autoai,
title={Autoai: Automating the end-to-end ai lifecycle with humans-in-the-loop},
author={Wang, Dakuo and Ram, Parikshit and Weidele, Daniel Karl I and Liu, Sijia and Muller, Michael and Weisz, Justin D and Valente, Abel and Chaudhary, Arunima and Torres, Dustin and Samulowitz, Horst and others},
booktitle={Proceedings of the 25th International Conference on Intelligent User Interfaces Companion},
pages={77--78},
year={2020}
}
@incollection{joshi2020amazon,
title={Amazons machine learning toolkit: Sagemaker},
author={Joshi, Ameet V},
booktitle={Machine Learning and Artificial Intelligence},
pages={233--243},
year={2020},
publisher={Springer}
}
@inproceedings{baylor2017tfx,
title={Tfx: A tensorflow-based production-scale machine learning platform},
author={Baylor, Denis and Breck, Eric and Cheng, Heng-Tze and Fiedel, Noah and Foo, Chuan Yu and Haque, Zakaria and Haykal, Salem and Ispir, Mustafa and Jain, Vihan and Koc, Levent and others},
booktitle={Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining},
pages={1387--1395},
year={2017}
}
@article{thiee2021systematic,
title={A systematic literature review of machine learning canvases},
author={Thi{\'e}e, Lukas-Walter},
journal={INFORMATIK 2021},
year={2021},
publisher={Gesellschaft f{\"u}r Informatik, Bonn}
}
@inproceedings{raji2020closing,
title={Closing the AI accountability gap: Defining an end-to-end framework for internal algorithmic auditing},
author={Raji, Inioluwa Deborah and Smart, Andrew and White, Rebecca N and Mitchell, Margaret and Gebru, Timnit and Hutchinson, Ben and Smith-Loud, Jamila and Theron, Daniel and Barnes, Parker},
booktitle={Proceedings of the 2020 conference on fairness, accountability, and transparency},
pages={33--44},
year={2020}
}
@article{prado2020bonseyes,
title={Bonseyes AI pipeline—Bringing AI to you: End-to-end integration of data, algorithms, and deployment tools},
author={Prado, Miguel De and Su, Jing and Saeed, Rabia and Keller, Lorenzo and Vallez, Noelia and Anderson, Andrew and Gregg, David and Benini, Luca and Llewellynn, Tim and Ouerhani, Nabil and others},
journal={ACM Transactions on Internet of Things},
volume={1},
number={4},
pages={1--25},
year={2020},
publisher={ACM New York, NY, USA}
}
@inproceedings{john2020ai,
title={AI Deployment Architecture: Multi-Case Study for Key Factor Identification},
author={John, Meenu Mary and Olsson, Helena Holmstr{\"o}m and Bosch, Jan},
booktitle={2020 27th Asia-Pacific Software Engineering Conference (APSEC)},
pages={395--404},
year={2020},
organization={IEEE}
}
@incollection{bosch2021engineering,
title={Engineering ai systems: A research agenda},
author={Bosch, Jan and Olsson, Helena Holmstr{\"o}m and Crnkovic, Ivica},
booktitle={Artificial Intelligence Paradigms for Smart Cyber-Physical Systems},
pages={1--19},
year={2021},
publisher={IGI global}
}
@article{klaise2021alibi,
title={Alibi Explain: algorithms for explaining machine learning models},
author={Klaise, Janis and Van Looveren, Arnaud and Vacanti, Giovanni and Coca, Alexandru},
journal={Journal of Machine Learning Research},
volume={22},
number={181},
pages={1--7},
year={2021}
}
@misc{jurafsky2019speech,
title={Speech and Language Processing (3rd (draft) ed.)},
author={Jurafsky, Dan and Martin, James H},
year={2019},
publisher={Stanford Univ}
}
@book{shull2007guide,
title={Guide to advanced empirical software engineering},
author={Shull, Forrest and Singer, Janice and Sj{\o}berg, Dag IK},
year={2007},
publisher={Springer}
}
@book{kleppmann2017designing,
title={Designing data-intensive applications: The big ideas behind reliable, scalable, and maintainable systems},
author={Kleppmann, Martin},
year={2017},
publisher={" O'Reilly Media, Inc."}
}
@article{davison2004principles,
title={Principles of canonical action research},
author={Davison, Robert and Martinsons, Maris G and Kock, Ned},
journal={Information systems journal},
volume={14},
number={1},
pages={65--86},
year={2004},
publisher={Wiley Online Library}
}
@article{krosnick1999survey,
title={Survey research},
author={Krosnick, Jon A},
journal={Annual review of psychology},
volume={50},
number={1},
pages={537--567},
year={1999},
publisher={Annual Reviews 4139 El Camino Way, PO Box 10139, Palo Alto, CA 94303-0139, USA}
}
@article{ritchie1978unix,
title={The UNIX time-sharing system},
author={Ritchie, Dennis M and Thompson, Ken},
journal={Bell System Technical Journal},
volume={57},
number={6},
pages={1905--1929},
year={1978},
publisher={Wiley Online Library}
}
@book{salus1994quarter,
title={A quarter century of UNIX},
author={Salus, Peter H},
year={1994},
publisher={ACM Press/Addison-Wesley Publishing Co.}
}
@inproceedings{hynes2017data,
title={The data linter: Lightweight, automated sanity checking for ml data sets},
author={Hynes, Nick and Sculley, D and Terry, Michael},
booktitle={NIPS MLSys Workshop},
volume={1},
year={2017}
}
@article{bishop1998robust,
title={Robust programming},
author={Bishop, Matt},
journal={handout for},
year={1998}
}
@article{arnaoudova2016linguistic,
title={Linguistic antipatterns: What they are and how developers perceive them},
author={Arnaoudova, Venera and Di Penta, Massimiliano and Antoniol, Giuliano},
journal={Empirical Software Engineering},
volume={21},
number={1},
pages={104--158},
year={2016},
publisher={Springer}
}
@inproceedings{blackwell2001cognitive,
title={Cognitive dimensions of notations: Design tools for cognitive technology},
author={Blackwell, Alan F and Britton, Carol and Cox, Anna and Green, Thomas RG and Gurr, Corin and Kadoda, Gada and Kutar, Maria S and Loomes, Martin and Nehaniv, Chrystopher L and Petre, Marian and others},
booktitle={International conference on cognitive technology},
pages={325--341},
year={2001},
organization={Springer}
}
@inproceedings{butler2009relating,
title={Relating identifier naming flaws and code quality: An empirical study},
author={Butler, Simon and Wermelinger, Michel and Yu, Yijun and Sharp, Helen},
booktitle={2009 16th Working Conference on Reverse Engineering},
pages={31--35},
year={2009},
organization={IEEE}
}
@article{deissenboeck2006concise,
title={Concise and consistent naming},
author={Deissenboeck, Florian and Pizka, Markus},
journal={Software Quality Journal},
volume={14},
number={3},
pages={261--282},
year={2006},
publisher={Springer}
}
@article{hand2001idiot,
title={Idiot's Bayes—not so stupid after all?},
author={Hand, David J and Yu, Keming},
journal={International statistical review},
volume={69},
number={3},
pages={385--398},
year={2001},
publisher={Wiley Online Library}
}
@article{beltagy2019scibert,
title={SciBERT: A pretrained language model for scientific text},
author={Beltagy, Iz and Lo, Kyle and Cohan, Arman},
journal={arXiv preprint arXiv:1903.10676},
year={2019}
}
@inproceedings{Lo2020S2ORCTS,
title={S2ORC: The Semantic Scholar Open Research Corpus},
author={Kyle Lo and Lucy Lu Wang and Mark Neumann and Rodney Michael Kinney and Daniel S. Weld},
booktitle={ACL},
year={2020}
}
@article{wang2019review,
title={A review of microsoft academic services for science of science studies},
author={Wang, Kuansan and Shen, Zhihong and Huang, Chiyuan and Wu, Chieh-Han and Eide, Darrin and Dong, Yuxiao and Qian, Junjie and Kanakia, Anshul and Chen, Alvin and Rogahn, Richard},
journal={Frontiers in Big Data},
volume={2},
pages={45},
year={2019},
publisher={Frontiers Media SA}
}
@techreport{buckley1985implementation,
title={Implementation of the SMART information retrieval system},
author={Buckley, Chris},
year={1985},
institution={Cornell University}
}
@article{mikolov2013efficient,
title={Efficient estimation of word representations in vector space},
author={Mikolov, Tomas and Chen, Kai and Corrado, Greg and Dean, Jeffrey},
journal={arXiv preprint arXiv:1301.3781},
year={2013}
}
@article{el2021automatic,
title={Automatic text summarization: A comprehensive survey},
author={El-Kassas, Wafaa S and Salama, Cherif R and Rafea, Ahmed A and Mohamed, Hoda K},
journal={Expert Systems with Applications},
volume={165},
pages={113679},
year={2021},
publisher={Elsevier}
}
@inproceedings{berkovsky2008aspect,
title={Aspect-based personalized text summarization},
author={Berkovsky, Shlomo and Baldwin, Timothy and Zukerman, Ingrid},
booktitle={International Conference on Adaptive Hypermedia and Adaptive Web-Based Systems},
pages={267--270},
year={2008},
organization={Springer}
}
@article{hayashi2021wikiasp,
title={WikiAsp: A dataset for multi-domain aspect-based summarization},
author={Hayashi, Hiroaki and Budania, Prashant and Wang, Peng and Ackerson, Chris and Neervannan, Raj and Neubig, Graham},
journal={Transactions of the Association for Computational Linguistics},
volume={9},
pages={211--225},
year={2021},
publisher={MIT Press}
}
@article{iwatsuki2022extraction,
title={Extraction and evaluation of formulaic expressions used in scholarly papers},
author={Iwatsuki, Kenichi and Boudin, Florian and Aizawa, Akiko},
journal={Expert Systems with Applications},
volume={187},
pages={115840},
year={2022},
publisher={Elsevier}
}
@inproceedings{iwatsuki2021communicative,
title={Communicative-Function-Based Sentence Classification for Construction of an Academic Formulaic Expression Database},
author={Iwatsuki, Kenichi and Aizawa, Akiko},
booktitle={Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume},
pages={3476--3497},
year={2021}
}
@article{iwatsuki2021extraction,
title={Extraction of Formulaic Expressions from Scientific Papers},
author={Iwatsuki, Kenichi and Aizawa, Akiko},
journal={methods},
volume={362},
pages={7--469},
year={2021}
}
@inproceedings{iwatsuki2020evaluation,
title={An evaluation dataset for identifying communicative functions of sentences in English scholarly papers},
author={Iwatsuki, Kenichi and Boudin, Florian and Aizawa, Akiko},
booktitle={12th Conference on Language Resources and Evaluation (LREC 2020)},
year={2020}
}
@article{cohen1960coefficient,
title={A coefficient of agreement for nominal scales},
author={Cohen, Jacob},
journal={Educational and psychological measurement},
volume={20},
number={1},
pages={37--46},
year={1960},
publisher={Sage Publications Sage CA: Thousand Oaks, CA}
}
@book{schutze2008introduction,
title={Introduction to information retrieval},
author={Sch{\"u}tze, Hinrich and Manning, Christopher D and Raghavan, Prabhakar},
volume={39},
year={2008},
publisher={Cambridge University Press Cambridge}
}
@article{miller1956magical,
title={The magical number seven, plus or minus two: Some limits on our capacity for processing information.},
author={Miller, George A},
journal={Psychological review},
volume={63},
number={2},
pages={81},
year={1956},
publisher={American Psychological Association}
}
@book{martin2009clean,
title={Clean code: a handbook of agile software craftsmanship},
author={Martin, Robert C},
year={2009},
publisher={Pearson Education}
}
@inproceedings{Chen_2016,
doi = {10.1145/2939672.2939785},
url = {https://doi.org/10.1145\%2F2939672.2939785},
year = 2016,
month = {aug},
publisher = {{ACM}},
author = {Tianqi Chen and Carlos Guestrin},
title = {{XGBoost}},
booktitle = {Proceedings of the 22nd {ACM} {SIGKDD} International Conference on Knowledge Discovery and Data Mining}
}
@article{food2019proposed,
title={Proposed regulatory framework for modifications to artificial intelligence/machine learning (AI/ML)-based software as a medical device (SaMD)},
author={Food and Drug Administration and others},
year={2019},
publisher={Department of Health and Human Services (United States)}
}
@inproceedings{moritz2018ray,
title={Ray: A distributed framework for emerging $\{$AI$\}$ applications},
author={Moritz, Philipp and Nishihara, Robert and Wang, Stephanie and Tumanov, Alexey and Liaw, Richard and Liang, Eric and Elibol, Melih and Yang, Zongheng and Paul, William and Jordan, Michael I and others},
booktitle={13th USENIX Symposium on Operating Systems Design and Implementation (OSDI 18)},
pages={561--577},
year={2018}
}
@article{rivest2021level,
title={level classification of scientific publications: A comparison of deep learning, direct citation and bibliographic coupling},
author={Rivest, Maxime and Vignola-Gagn{\'e}, Etienne and Archambault, {\'E}ric},
journal={PloS one},
volume={16},
number={5},
pages={e0251493},
year={2021},
publisher={Public Library of Science San Francisco, CA USA}
}
@article{maron1961automatic,
title={Automatic indexing: an experimental inquiry},
author={Maron, Melvin Earl},
journal={Journal of the ACM (JACM)},
volume={8},
number={3},
pages={404--417},
year={1961},
publisher={ACM New York, NY, USA}
}
@article{vaswani2017attention,
title={Attention is all you need},
author={Vaswani, Ashish and Shazeer, Noam and Parmar, Niki and Uszkoreit, Jakob and Jones, Llion and Gomez, Aidan N and Kaiser, {\L}ukasz and Polosukhin, Illia},
journal={Advances in neural information processing systems},
volume={30},
year={2017}
}
@misc{Procida_Diataxis_documentation_framework,
author = {Procida, Daniele},
title = {{Diátaxis documentation framework}},
url = {https://diataxis.fr/}
}