{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,25]],"date-time":"2026-06-25T20:57:39Z","timestamp":1782421059518,"version":"3.54.5"},"publisher-location":"New York, NY, USA","reference-count":156,"publisher":"ACM","license":[{"start":{"date-parts":[[2021,3,1]],"date-time":"2021-03-01T00:00:00Z","timestamp":1614556800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2021,3,3]]},"DOI":"10.1145\/3442188.3445922","type":"proceedings-article","created":{"date-parts":[[2021,3,3]],"date-time":"2021-03-03T01:26:24Z","timestamp":1614734784000},"page":"610-623","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":4885,"title":["On the Dangers of Stochastic Parrots"],"prefix":"10.1145","author":[{"given":"Emily M.","family":"Bender","sequence":"first","affiliation":[{"name":"University of Washington, Seattle, WA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Timnit","family":"Gebru","sequence":"additional","affiliation":[{"name":"Black in AI, Palo Alto, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Angelina","family":"McMillan-Major","sequence":"additional","affiliation":[{"name":"University of Washington, Seattle, WA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shmargaret","family":"Shmitchell","sequence":"additional","affiliation":[{"name":"The Aether"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2021,3]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"Hussein M Adam Robert D Bullard and Elizabeth Bell. 2001. Faces of environmental racism: Confronting issues of global justice. Rowman & Littlefield."},{"key":"e_1_3_2_1_2_1","unstructured":"Chris Alberti Kenton Lee and Michael Collins. 2019. A BERT Baseline for the Natural Questions. arXiv:1901.08634 [cs.CL]"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.2307\/3312397"},{"key":"e_1_3_2_1_4_1","volume-title":"Discrimination: What it is, and how to cope. https:\/\/www.apa.org\/topics\/discrimination","author":"American Psychological Association","year":"2019","unstructured":"American Psychological Association. 2019. Discrimination: What it is, and how to cope. https:\/\/www.apa.org\/topics\/discrimination (2019)."},{"key":"e_1_3_2_1_5_1","unstructured":"Dario Amodei and Daniel Hernandez. 2018. AI and Compute. https:\/\/openai. com\/blog\/ai-and-compute\/"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11027-010-9220-7"},{"key":"e_1_3_2_1_7_1","volume-title":"Natural Language Watermarking and Tamperproofing. In International Workshop on Information Hiding. Springer, 196--212","author":"Atallah Mikhail J","year":"2002","unstructured":"Mikhail J Atallah, Victor Raskin, Christian F Hempelmann, Mercan Karahan, Radu Sion, Umut Topkara, and Katrina E Triezenberg. 2002. Natural Language Watermarking and Tamperproofing. In International Workshop on Information Hiding. Springer, 196--212."},{"key":"e_1_3_2_1_8_1","volume-title":"Effectiveness of Self-Supervised Pre-Training for ASR. In ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). 7694--7698","author":"Baevski Alexei","year":"2020","unstructured":"Alexei Baevski and Abdelrahman Mohamed. 2020. Effectiveness of Self-Supervised Pre-Training for ASR. In ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). 7694--7698."},{"key":"e_1_3_2_1_9_1","unstructured":"Michael Barera. 2020. Mind the Gap: Addressing Structural Equity and Inclusion on Wikipedia. (2020). Accessible at http:\/\/hdl.handle.net\/10106\/29572."},{"key":"e_1_3_2_1_10_1","first-page":"723","article-title":"Indigenous peoples, racism and the environment","volume":"49","author":"Barsh Russel","year":"1990","unstructured":"Russel Barsh. 1990. Indigenous peoples, racism and the environment. Meanjin 49, 4 (1990), 723.","journal-title":"Meanjin"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W19-3805"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00041"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1"},{"key":"e_1_3_2_1_15_1","volume-title":"Race After Technology: Abolitionist Tools for the New Jim Code","author":"Benjamin Ruha","unstructured":"Ruha Benjamin. 2019. Race After Technology: Abolitionist Tools for the New Jim Code. Polity Press, Cambridge, UK."},{"key":"e_1_3_2_1_16_1","volume-title":"Data Waste. Harvard International Law Journal 61","author":"Bietti Elettra","year":"2020","unstructured":"Elettra Bietti and Roxana Vatanparast. 2020. Data Waste. Harvard International Law Journal 61 (2020)."},{"key":"e_1_3_2_1_17_1","volume-title":"People.Policy.Place Seminar","author":"Bird Steven","year":"2016","unstructured":"Steven Bird. 2016. Social Mobile Technologies for Reconnecting Indigenous and Immigrant Communities.. In People.Policy.Place Seminar. Northern Institute, Charles Darwin University, Darwin, Australia. https:\/\/www.cdu.edu.au\/sites\/default\/files\/the-northern-institute\/ppp-bird-20160128-4up.pdf"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00158"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1"},{"key":"e_1_3_2_1_20_1","volume-title":"Proceedings of the 2007 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning (EMNLP-CoNLL)","author":"Brants Thorsten","unstructured":"Thorsten Brants, Ashok C. Popat, Peng Xu, Franz J. Och, and Jeffrey Dean. 2007. Large Language Models in Machine Translation. In Proceedings of the 2007 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning (EMNLP-CoNLL). Association for Computational Linguistics, Prague, Czech Republic, 858--867. https:\/\/www.aclweb.org\/anthology\/D07-1090"},{"key":"e_1_3_2_1_21_1","volume-title":"Proceedings of the 37th International Conference on Machine Learning.","author":"Bras Ronan Le","year":"2020","unstructured":"Ronan Le Bras, Swabha Swayamdipta, Chandra Bhagavatula, Rowan Zellers, Matthew E Peters, Ashish Sabharwal, and Yejin Choi. 2020. Adversarial Filters of Dataset Biases. In Proceedings of the 37th International Conference on Machine Learning."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1037\/0278-7393.22.6.1482"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/2858036.2858379"},{"key":"e_1_3_2_1_25_1","volume-title":"Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020","author":"Brown Tom B.","year":"2020","unstructured":"Tom B. Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared Kaplan, Prafulla Dhariwal, Arvind Neelakantan, Pranav Shyam, Girish Sastry, Amanda Askell, Sandhini Agarwal, Ariel Herbert-Voss, Gretchen Krueger, Tom Henighan, Rewon Child, Aditya Ramesh, Daniel M. Ziegler, Jeffrey Wu, Clemens Winter, Christopher Hesse, Mark Chen, Eric Sigler, Mateusz Litwin, Scott Gray, Benjamin Chess, Jack Clark, Christopher Berner, Sam McCandlish, Alec Radford, Ilya Sutskever, and Dario Amodei. 2020. Language Models are Few-Shot Learners. In Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, NeurIPS 2020, December 6-12, 2020, virtual, Hugo Larochelle, Marc'Aurelio Ranzato, Raia Hadsell, Maria-Florina Balcan, and Hsuan-Tien Lin (Eds.). https:\/\/proceedings.neurips.cc\/paper\/2020\/hash\/1457c0d6bfcb4967418bfb8ac142f64a-Abstract.html"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/1150402.1150464"},{"key":"e_1_3_2_1_27_1","volume-title":"Confronting environmental racism: Voices from the grassroots","author":"Bullard Robert D","unstructured":"Robert D Bullard. 1993. Confronting environmental racism: Voices from the grassroots. South End Press."},{"key":"e_1_3_2_1_28_1","unstructured":"Nicholas Carlini Florian Tramer Eric Wallace Matthew Jagielski Ariel Herbert-Voss Katherine Lee Adam Roberts Tom Brown Dawn Song Ulfar Erlingsson Alina Oprea and Colin Raffel. 2020. Extracting Training Data from Large Language Models. arXiv:2012.07805 [cs.CR]"},{"key":"e_1_3_2_1_29_1","volume-title":"Using Language","author":"Clark Herbert H.","unstructured":"Herbert H. Clark. 1996. Using Language. Cambridge University Press, Cambridge."},{"key":"e_1_3_2_1_30_1","volume-title":"Clark and Adrian Bangerter","author":"Herbert","year":"2004","unstructured":"Herbert H. Clark and Adrian Bangerter. 2004. Changing ideas about reference. In Experimental Pragmatics. Springer, 25--49."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jml.2003.08.004"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0022-5371(83)90189-5"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1016\/0010-0277(86)"},{"key":"e_1_3_2_1_34_1","volume-title":"Demarginalizing the intersection of race and sex: A Black feminist critique of antidiscrimination doctrine, feminist theory and antiracist politics","author":"Crenshaw Kimberl\u00e9","year":"1989","unstructured":"Kimberl\u00e9 Crenshaw. 1989. Demarginalizing the intersection of race and sex: A Black feminist critique of antidiscrimination doctrine, feminist theory and antiracist politics. The University of Chicago Legal Forum (1989), 139."},{"key":"e_1_3_2_1_35_1","volume-title":"The Five Hundred Year Rebellion: Indigenous Movements and the Decolonization of History in Bolivia","author":"Dangl Benjamin","unstructured":"Benjamin Dangl. 2019. The Five Hundred Year Rebellion: Indigenous Movements and the Decolonization of History in Bolivia. AK Press."},{"key":"e_1_3_2_1_36_1","volume-title":"Media bias, perspective, and state repression: The Black Panther Party","author":"Davenport Christian","unstructured":"Christian Davenport. 2009. Media bias, perspective, and state repression: The Black Panther Party. Cambridge University Press."},{"key":"e_1_3_2_1_37_1","volume-title":"Course in General Linguistics","author":"de Saussure Ferdinand","unstructured":"Ferdinand de Saussure. 1959. Course in General Linguistics. The Philosophical Society, New York. Translated by Wade Baskin."},{"key":"e_1_3_2_1_38_1","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops. 52--59","author":"de Vries Terrance","unstructured":"Terrance de Vries, Ishan Misra, Changhan Wang, and Laurens van der Maaten. 2019. Does object recognition work for everyone?. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops. 52--59."},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1"},{"key":"e_1_3_2_1_40_1","unstructured":"Maeve Duggan. 2017. Online Harassment 2017. Pew Research Center."},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1146\/annurev.soc.30.012703.110603"},{"key":"e_1_3_2_1_42_1","volume-title":"Proceedings of the International AAAI Conference on Web and Social Media","volume":"10","author":"Fast Ethan","year":"2016","unstructured":"Ethan Fast, Tina Vachovsky, and Michael Bernstein. 2016. Shirtless and Dangerous: Quantifying Linguistic Signals of Gender Bias in an Online Fiction Writing Community. In Proceedings of the International AAAI Conference on Web and Social Media, Vol. 10."},{"key":"e_1_3_2_1_43_1","volume-title":"Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity. arXiv:2101.03961 [cs.LG]","author":"Fedus William","year":"2021","unstructured":"William Fedus, Barret Zoph, and Noam Shazeer. 2021. Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity. arXiv:2101.03961 [cs.LG]"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1"},{"key":"e_1_3_2_1_45_1","volume-title":"Proceedings of the 2nd Workshop on Abusive Language Online (ALW2). Association for Computational Linguistics","author":"Fi\u0161er Darja","year":"2018","unstructured":"Darja Fi\u0161er, Ruihong Huang, Vinodkumar Prabhakaran, Rob Voigt, Zeerak Waseem, and Jacqueline Wernimont (Eds.). 2018. Proceedings of the 2nd Workshop on Abusive Language Online (ALW2). Association for Computational Linguistics, Brussels, Belgium. https:\/\/www.aclweb.org\/anthology\/W18-5100"},{"key":"e_1_3_2_1_46_1","volume-title":"Prejudices in cultural contexts: shared stereotypes (gender, age) versus variable stereotypes (race, ethnicity, religion). Perspectives on psychological science 12, 5","author":"Fiske Susan T","year":"2017","unstructured":"Susan T Fiske. 2017. Prejudices in cultural contexts: shared stereotypes (gender, age) versus variable stereotypes (race, ethnicity, religion). Perspectives on psychological science 12, 5 (2017), 791--799."},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1609\/icwsm.v12i1.14991"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1145\/2207676.2208562"},{"key":"e_1_3_2_1_49_1","volume-title":"Hendry","author":"Friedman Batya","year":"2019","unstructured":"Batya Friedman and David G. Hendry. 2019. Value Sensitive Design: Shaping Technology with Moral Imagination. MIT Press."},{"key":"e_1_3_2_1_50_1","unstructured":"Batya Friedman Peter H. Kahn Jr. and Alan Borning. 2006. Value sensitive design and information systems. In Human-Computer Interaction in Management Information Systems: Foundations P Zhang and D Galletta (Eds.). M. E. Sharpe Armonk NY 348--372."},{"key":"e_1_3_2_1_51_1","volume-title":"The Pile: An 800GB Dataset of Diverse Text for Language Modeling. arXiv:2101.00027 [cs.CL]","author":"Gao Leo","year":"2020","unstructured":"Leo Gao, Stella Biderman, Sid Black, Laurence Golding, Travis Hoppe, Charles Foster, Jason Phang, Horace He, Anish Thite, Noa Nabeshima, Shawn Presser, and Connor Leahy. 2020. The Pile: An 800GB Dataset of Diverse Text for Language Modeling. arXiv:2101.00027 [cs.CL]"},{"key":"e_1_3_2_1_52_1","volume-title":"Hanna Wallach, Hal Daum\u00e9 III, and Kate Crawford.","author":"Gebru Timnit","year":"2020","unstructured":"Timnit Gebru, Jamie Morgenstern, Briana Vecchione, Jennifer Wortman Vaughan, Hanna Wallach, Hal Daum\u00e9 III, and Kate Crawford. 2020. Datasheets for Datasets. arXiv:1803.09010 [cs.DB]"},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1"},{"key":"e_1_3_2_1_54_1","volume-title":"Detecting Emergent Intersectional Biases: Contextualized Word Embeddings Contain a Distribution of Human-like Biases. arXiv preprint arXiv:2006.03955","author":"Guo Wei","year":"2020","unstructured":"Wei Guo and Aylin Caliskan. 2020. Detecting Emergent Intersectional Biases: Contextualized Word Embeddings Contain a Distribution of Human-like Biases. arXiv preprint arXiv:2006.03955 (2020)."},{"key":"e_1_3_2_1_55_1","first-page":"741","article-title":"Subjective decisionmaking and unconscious discrimination","volume":"56","author":"Hart Melissa","year":"2004","unstructured":"Melissa Hart. 2004. Subjective decisionmaking and unconscious discrimination. Alabama Law Review 56 (2004), 741.","journal-title":"Alabama Law Review"},{"key":"e_1_3_2_1_56_1","unstructured":"Deborah Hellman. 2008. When is Discrimination Wrong? Harvard University Press."},{"key":"e_1_3_2_1_57_1","first-page":"1","article-title":"Towards the Systematic Reporting of the Energy and Carbon Footprints of Machine Learning","volume":"21","author":"Henderson Peter","year":"2020","unstructured":"Peter Henderson, Jieru Hu, Joshua Romoff, Emma Brunskill, Dan Jurafsky, and Joelle Pineau. 2020. Towards the Systematic Reporting of the Energy and Carbon Footprints of Machine Learning. Journal of Machine Learning Research 21, 248 (2020), 1--43. http:\/\/jmlr.org\/papers\/v21\/20-312.html","journal-title":"Journal of Machine Learning Research"},{"key":"e_1_3_2_1_58_1","volume-title":"Distilling the knowledge in a neural network. arXiv preprint arXiv:1503.02531","author":"Hinton Geoffrey","year":"2015","unstructured":"Geoffrey Hinton, Oriol Vinyals, and Jeff Dean. 2015. Distilling the knowledge in a neural network. arXiv preprint arXiv:1503.02531 (2015)."},{"key":"e_1_3_2_1_59_1","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003825"},{"key":"e_1_3_2_1_60_1","unstructured":"Hongzhao Huang and Fuchun Peng. 2019. An Empirical Study of Efficient ASR Rescoring with Transformers. arXiv:1910.11450 [cs.CL]"},{"key":"e_1_3_2_1_61_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1"},{"key":"e_1_3_2_1_62_1","doi-asserted-by":"publisher","DOI":"10.1145\/3351095.3372829"},{"key":"e_1_3_2_1_63_1","doi-asserted-by":"publisher","DOI":"10.1177\/0160597619832049"},{"key":"e_1_3_2_1_64_1","unstructured":"Leslie Kay Jones. 2020. Twitter wants you to know that you're still SOL if you get a death threat --- unless you're President Donald Trump. (2020). https:\/\/medium.com\/@agua.carbonica\/twitter-wants-you-to-know-that-youre-still-sol-if-you-get-a-death-threat-unless-you-re-a5cce316b706."},{"key":"e_1_3_2_1_65_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1"},{"key":"e_1_3_2_1_66_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2018"},{"key":"e_1_3_2_1_67_1","volume-title":"Mohammad Atari, and Morteza Dehghani.","author":"Kennedy Brendan","year":"2018","unstructured":"Brendan Kennedy, Drew Kogon, Kris Coombs, Joseph Hoover, Christina Park, Gwenyth Portillo-Wightman, Aida Mostafazadeh Davani, Mohammad Atari, and Morteza Dehghani. 2018. A typology and coding manual for the study of hate-based rhetoric. PsyArXiv. July 18 (2018)."},{"key":"e_1_3_2_1_68_1","volume-title":"Performing a project premortem. Harvard business review 85, 9","author":"Klein Gary","year":"2007","unstructured":"Gary Klein. 2007. Performing a project premortem. Harvard business review 85, 9 (2007), 18--19."},{"key":"e_1_3_2_1_69_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W19-3823"},{"key":"e_1_3_2_1_70_1","volume-title":"ALBERT: A Lite BERT for Self-supervised Learning of Language Representations. arXiv preprint arXiv:1909.11942","author":"Lan Zhenzhong","year":"2019","unstructured":"Zhenzhong Lan, Mingda Chen, Sebastian Goodman, Kevin Gimpel, Piyush Sharma, and Radu Soricut. 2019. ALBERT: A Lite BERT for Self-supervised Learning of Language Representations. arXiv preprint arXiv:1909.11942 (2019)."},{"key":"e_1_3_2_1_71_1","doi-asserted-by":"publisher","DOI":"10.1145\/2998181.2998275"},{"key":"e_1_3_2_1_72_1","doi-asserted-by":"publisher","DOI":"10.1145\/1518701.1518875"},{"key":"e_1_3_2_1_73_1","unstructured":"Dmitry Lepikhin HyoukJoong Lee Yuanzhong Xu Dehao Chen Orhan Firat Yanping Huang Maxim Krikun Noam Shazeer and Zhifeng Chen. 2020. GShard: Scaling Giant Models with Conditional Computation and Automatic Sharding. arXiv:2006.16668 [cs.CL]"},{"key":"e_1_3_2_1_74_1","volume-title":"Roberta: A robustly optimized bert pretraining approach. arXiv preprint arXiv:1907.11692","author":"Liu Yinhan","year":"2019","unstructured":"Yinhan Liu, Myle Ott, Naman Goyal, Jingfei Du, Mandar Joshi, Danqi Chen, Omer Levy, Mike Lewis, Luke Zettlemoyer, and Veselin Stoyanov. 2019. Roberta: A robustly optimized bert pretraining approach. arXiv preprint arXiv:1907.11692 (2019)."},{"key":"e_1_3_2_1_75_1","volume-title":"Wilson","author":"Lottick Kadan","year":"2019","unstructured":"Kadan Lottick, Silvia Susai, Sorelle A. Friedler, and Jonathan P. Wilson. 2019. Energy Usage Reports: Environmental awareness as part of algorithmic accountability. arXiv:1911.08354 [cs.LG]"},{"key":"e_1_3_2_1_76_1","doi-asserted-by":"publisher","DOI":"10.12738\/mejrs.2017.2.1.0110"},{"key":"e_1_3_2_1_77_1","volume-title":"Proceedings of the 13th Conference of the Association for Machine Translation in the Americas (Volume 1: Research Track). Association for Machine Translation in the Americas","author":"Martindale Marianna","year":"2018","unstructured":"Marianna Martindale and Marine Carpuat. 2018. Fluency Over Adequacy: A Pilot Study in Measuring User Trust in Imperfect MT. In Proceedings of the 13th Conference of the Association for Machine Translation in the Americas (Volume 1: Research Track). Association for Machine Translation in the Americas, Boston, MA, 13--25. https:\/\/www.aclweb.org\/anthology\/W18-1803"},{"key":"e_1_3_2_1_78_1","doi-asserted-by":"publisher","DOI":"10.1111\/j.1749-6632.1984.tb14764.x"},{"key":"e_1_3_2_1_79_1","doi-asserted-by":"publisher","DOI":"10.1017\/9781108641302"},{"key":"e_1_3_2_1_81_1","volume-title":"News coverage and social protest: How the media's protect paradigm exacerbates social conflict. Journal of Dispute Resolution","author":"McLeod Douglas M","year":"2007","unstructured":"Douglas M McLeod. 2007. News coverage and social protest: How the media's protect paradigm exacerbates social conflict. Journal of Dispute Resolution (2007), 185."},{"key":"e_1_3_2_1_82_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/K16-1006"},{"key":"e_1_3_2_1_83_1","doi-asserted-by":"publisher","DOI":"10.3389\/frai.2020.00055"},{"key":"e_1_3_2_1_84_1","doi-asserted-by":"publisher","DOI":"10.1177\/1350506818765318"},{"key":"e_1_3_2_1_85_1","volume-title":"Proceedings of the 26th International Conference on Neural Information Processing Systems -","volume":"2","author":"Mikolov Tomas","year":"2013","unstructured":"Tomas Mikolov, Ilya Sutskever, Kai Chen, Greg Corrado, and Jeffrey Dean. 2013. Distributed Representations of Words and Phrases and Their Compositionality. In Proceedings of the 26th International Conference on Neural Information Processing Systems - Volume 2 (Lake Tahoe, Nevada) (NIPS'13). Curran Associates Inc., Red Hook, NY, USA, 3111--3119."},{"key":"e_1_3_2_1_86_1","doi-asserted-by":"publisher","DOI":"10.1145\/3287560.3287596"},{"key":"e_1_3_2_1_87_1","volume-title":"Proceedings of the ACL 2010 Conference Short Papers. Association for Computational Linguistics","author":"Robert","year":"2041","unstructured":"Robert C. Moore and William Lewis. 2010. Intelligent Selection of Language Model Training Data. In Proceedings of the ACL 2010 Conference Short Papers. Association for Computational Linguistics, Uppsala, Sweden, 220--224. https:\/\/www.aclweb.org\/anthology\/P10-2041"},{"key":"e_1_3_2_1_88_1","volume-title":"Microaggressions and Traumatic Stress: Theory, Research, and Clinical Treatment","author":"Nadal Kevin L.","unstructured":"Kevin L. Nadal. 2018. Microaggressions and Traumatic Stress: Theory, Research, and Clinical Treatment. American Psychological Association. https:\/\/books.google.com\/books?id=ogzhswEACAAJ"},{"key":"e_1_3_2_1_89_1","doi-asserted-by":"publisher","DOI":"10.1145\/191666.191703"},{"key":"e_1_3_2_1_90_1","doi-asserted-by":"publisher","DOI":"10.1145\/1240866.1241046"},{"key":"e_1_3_2_1_91_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1"},{"key":"e_1_3_2_1_92_1","volume-title":"The Argonauts","author":"Nelson Maggie","unstructured":"Maggie Nelson. 2015. The Argonauts. Graywolf Press, Minneapolis."},{"key":"e_1_3_2_1_93_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1"},{"key":"e_1_3_2_1_94_1","volume-title":"Algorithms of Oppression: How Search Engines Reinforce Racism","author":"Noble Safiya Umoja","unstructured":"Safiya Umoja Noble. 2018. Algorithms of Oppression: How Search Engines Reinforce Racism. NYU Press."},{"key":"e_1_3_2_1_95_1","unstructured":"Debora Nozza Federico Bianchi and Dirk Hovy. 2020. What the [MASK]? Making Sense of Language-Specific BERT Models. arXiv:2003.02912 [cs.CL]"},{"key":"e_1_3_2_1_96_1","first-page":"397","article-title":"Where do we stand with newspaper data? Mobilization","volume":"10","author":"Ortiz David","year":"2005","unstructured":"David Ortiz, Daniel Myers, Eugene Walls, and Maria-Elena Diaz. 2005. Where do we stand with newspaper data? Mobilization: An International Quarterly 10, 3 (2005), 397--419.","journal-title":"An International Quarterly"},{"key":"e_1_3_2_1_97_1","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0146487"},{"key":"e_1_3_2_1_98_1","doi-asserted-by":"publisher","DOI":"10.3115\/v1"},{"key":"e_1_3_2_1_99_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1"},{"key":"e_1_3_2_1_100_1","unstructured":"Pew. 2018. Internet\/Broadband Fact Sheet. (2 2018). https:\/\/www.pewinternet. org\/fact-sheet\/internet-broadband\/"},{"key":"e_1_3_2_1_101_1","volume-title":"Oxford Research Encyclopedia of Linguistics","author":"Pine Aidan","unstructured":"Aidan Pine and Mark Turin. 2017. Language Revitalization. Oxford Research Encyclopedia of Linguistics."},{"key":"e_1_3_2_1_102_1","volume-title":"Contending stories: Narrative in social movements. Qualitative sociology 21, 4","author":"Polletta Francesca","year":"1998","unstructured":"Francesca Polletta. 1998. Contending stories: Narrative in social movements. Qualitative sociology 21, 4 (1998), 419--446."},{"key":"e_1_3_2_1_103_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1"},{"key":"e_1_3_2_1_104_1","doi-asserted-by":"publisher","DOI":"10.1080\/10455752.2016.1213013"},{"key":"e_1_3_2_1_105_1","unstructured":"Xipeng Qiu Tianxiang Sun Yige Xu Yunfan Shao Ning Dai and Xuanjing Huang. 2020. Pre-trained Models for Natural Language Processing: A Survey. arXiv:2003.08271 [cs.CL]"},{"key":"e_1_3_2_1_106_1","first-page":"9","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford Alec","year":"2019","unstructured":"Alec Radford, Jeffrey Wu, Rewon Child, David Luan, Dario Amodei, and Ilya Sutskever. 2019. Language models are unsupervised multitask learners. OpenAI Blog 1, 8 (2019), 9.","journal-title":"OpenAI Blog"},{"key":"e_1_3_2_1_107_1","first-page":"1","article-title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","volume":"21","author":"Raffel Colin","year":"2020","unstructured":"Colin Raffel, Noam Shazeer, Adam Roberts, Katherine Lee, Sharan Narang, Michael Matena, Yanqi Zhou, Wei Li, and Peter J. Liu. 2020. Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer. Journal of Machine Learning Research 21, 140 (2020), 1--67. http:\/\/jmlr.org\/papers\/v21\/20-074.html","journal-title":"Journal of Machine Learning Research"},{"key":"e_1_3_2_1_108_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1"},{"key":"e_1_3_2_1_109_1","volume-title":"Proceedings of the Third Workshop on Abusive Language Online. Association for Computational Linguistics","author":"Roberts Sarah T.","year":"2019","unstructured":"Sarah T. Roberts, Joel Tetreault, Vinodkumar Prabhakaran, and Zeerak Waseem (Eds.). 2019. Proceedings of the Third Workshop on Abusive Language Online. Association for Computational Linguistics, Florence, Italy. https:\/\/www.aclweb.org\/anthology\/W19-3500"},{"key":"e_1_3_2_1_110_1","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00349"},{"key":"e_1_3_2_1_111_1","doi-asserted-by":"publisher","DOI":"10.1109\/5.880083"},{"key":"e_1_3_2_1_112_1","volume-title":"Turing-NLG: A 17-billion-parameter language model by Microsoft. Microsoft Blog","author":"Rosset Corby","year":"2020","unstructured":"Corby Rosset. 2020. Turing-NLG: A 17-billion-parameter language model by Microsoft. Microsoft Blog (2020)."},{"key":"e_1_3_2_1_113_1","volume-title":"a distilled version of BERT: smaller, faster, cheaper and lighter. arXiv preprint arXiv:1910.01108","author":"Sanh Victor","year":"2019","unstructured":"Victor Sanh, Lysandre Debut, Julien Chaumond, and Thomas Wolf. 2019. DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter. arXiv preprint arXiv:1910.01108 (2019)."},{"key":"e_1_3_2_1_114_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1"},{"key":"e_1_3_2_1_115_1","doi-asserted-by":"publisher","DOI":"10.1145\/3381831"},{"key":"e_1_3_2_1_116_1","volume-title":"Gender stereotypes and the attribution of leadership traits: A cross-cultural comparison. Sex roles 51, 11-12","author":"Sczesny Sabine","year":"2004","unstructured":"Sabine Sczesny, Janine Bosak, Daniel Neff, and Birgit Schyns. 2004. Gender stereotypes and the attribution of leadership traits: A cross-cultural comparison. Sex roles 51, 11-12 (2004), 631--645."},{"key":"e_1_3_2_1_117_1","volume-title":"The Mathematical Theory of Communication","author":"Shannon Claude Elwood","unstructured":"Claude Elwood Shannon. 1949. The Mathematical Theory of Communication. University of Illinois Press, Urbana."},{"key":"e_1_3_2_1_118_1","doi-asserted-by":"crossref","unstructured":"Sheng Shen Zhen Dong Jiayu Ye Linjian Ma Zhewei Yao Amir Gholami Michael W. Mahoney and Kurt Keutzer. 2019. Q-BERT: Hessian Based Ultra Low Precision Quantization of BERT. arXiv:1909.05840 [cs.CL]","DOI":"10.1609\/aaai.v34i05.6409"},{"key":"e_1_3_2_1_119_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1"},{"key":"e_1_3_2_1_120_1","doi-asserted-by":"publisher","DOI":"10.1145\/2531602.2531625"},{"key":"e_1_3_2_1_121_1","volume-title":"Effective Sentence Scoring Method Using BERT for Speech Recognition. In Asian Conference on Machine Learning. 1081--1093","author":"Shin Joonbo","year":"2019","unstructured":"Joonbo Shin, Yoonhyung Lee, and Kyomin Jung. 2019. Effective Sentence Scoring Method Using BERT for Speech Recognition. In Asian Conference on Machine Learning. 1081--1093."},{"key":"e_1_3_2_1_122_1","volume-title":"Megatron-lm: Training multi-billion parameter language models using gpu model parallelism. arXiv preprint arXiv:1909.08053","author":"Shoeybi Mohammad","year":"2019","unstructured":"Mohammad Shoeybi, Mostofa Patwary, Raul Puri, Patrick LeGresley, Jared Casper, and Bryan Catanzaro. 2019. Megatron-lm: Training multi-billion parameter language models using gpu model parallelism. arXiv preprint arXiv:1909.08053 (2019)."},{"key":"e_1_3_2_1_123_1","volume-title":"Sarah Kreps, et al.","author":"Solaiman Irene","year":"2019","unstructured":"Irene Solaiman, Miles Brundage, Jack Clark, Amanda Askell, Ariel Herbert-Voss, Jeff Wu, Alec Radford, Gretchen Krueger, Jong Wook Kim, Sarah Kreps, et al. 2019. Release strategies and the social impacts of language models. arXiv preprint arXiv:1908.09203 (2019)."},{"key":"e_1_3_2_1_125_1","unstructured":"Robyn Speer. 2017. ConceptNet Numberbatch 17.04: better less-stereotyped word vectors. (2017). Blog post https:\/\/blog.conceptnet.io\/2017\/04\/24\/conceptnet-numberbatch-17-04-better-less-stereotyped-word-vectors\/."},{"key":"e_1_3_2_1_126_1","doi-asserted-by":"publisher","DOI":"10.1146\/annurev-psych-073115-103235"},{"key":"e_1_3_2_1_127_1","volume-title":"Our Oral History Journey1. The Oral History Review","author":"Srigley Katrina","year":"2019","unstructured":"Katrina Srigley and Lorraine Sutherland. 2019. Decolonizing, Indigenizing, and Learning Biskaaybiiyang in the Field: Our Oral History Journey1. The Oral History Review (2019)."},{"key":"e_1_3_2_1_128_1","doi-asserted-by":"publisher","DOI":"10.1073\/pnas"},{"key":"e_1_3_2_1_129_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1355"},{"key":"e_1_3_2_1_130_1","volume-title":"ERNIE: Enhanced Representation through Knowledge Integration. arXiv:1904.09223 [cs.CL]","author":"Sun Yu","year":"2019","unstructured":"Yu Sun, Shuohuan Wang, Yukun Li, Shikun Feng, Xuyi Chen, Han Zhang, Xin Tian, Danxiang Zhu, Hao Tian, and Hua Wu. 2019. ERNIE: Enhanced Representation through Knowledge Integration. arXiv:1904.09223 [cs.CL]"},{"key":"e_1_3_2_1_131_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6428"},{"key":"e_1_3_2_1_132_1","unstructured":"Yi Chern Tan and L Elisa Celis. 2019. Assessing social and intersectional biases in contextualized word representations. In Advances in Neural Information Processing Systems. 13230--13241."},{"key":"e_1_3_2_1_133_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1"},{"key":"e_1_3_2_1_134_1","volume-title":"Le","author":"Trinh Trieu H.","year":"2019","unstructured":"Trieu H. Trinh and Quoc V. Le. 2019. A Simple Method for Commonsense Reasoning. arXiv:1806.02847 [cs.AI]"},{"key":"e_1_3_2_1_135_1","doi-asserted-by":"publisher","DOI":"10.1145\/2998181.2998232"},{"key":"e_1_3_2_1_136_1","unstructured":"Ashish Vaswani Noam Shazeer Niki Parmar Jakob Uszkoreit Llion Jones Aidan N Gomez \u0141ukasz Kaiser and Illia Polosukhin. 2017. Attention is all you need. In Advances in neural information processing systems. 5998--6008."},{"key":"e_1_3_2_1_137_1","volume-title":"Proceedings of the Eleventh International Conference on Language Resources and Evaluation (LREC","author":"Voigt Rob","year":"2018","unstructured":"Rob Voigt, David Jurgens, Vinodkumar Prabhakaran, Dan Jurafsky, and Yulia Tsvetkov. 2018. RtGender: A Corpus for Studying Differential Responses to Gender. In Proceedings of the Eleventh International Conference on Language Resources and Evaluation (LREC 2018). European Language Resources Association (ELRA), Miyazaki, Japan. https:\/\/www.aclweb.org\/anthology\/L18-1445"},{"key":"e_1_3_2_1_138_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W18-5446"},{"key":"e_1_3_2_1_139_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1"},{"key":"e_1_3_2_1_140_1","volume-title":"Computer Power and Human Reason: From Judgment to Calculation","author":"Weizenbaum Joseph","unstructured":"Joseph Weizenbaum. 1976. Computer Power and Human Reason: From Judgment to Calculation. WH Freeman & Co."},{"key":"e_1_3_2_1_141_1","doi-asserted-by":"publisher","DOI":"10.1177\/1745691619893362"},{"key":"e_1_3_2_1_142_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1"},{"key":"e_1_3_2_1_143_1","unstructured":"World Bank. 2018. Indiviuals Using the Internet. (2018). https:\/\/data.worldbank. org\/indicator\/IT.NET.USER.ZS?end=2017amp;locations=USamp;start=2015"},{"key":"e_1_3_2_1_144_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1"},{"key":"e_1_3_2_1_145_1","volume-title":"ERNIE-GEN: An Enhanced Multi-Flow Pre-training and Fine-tuning Framework for Natural Language Generation. arXiv preprint arXiv:2001.11314","author":"Xiao Dongling","year":"2020","unstructured":"Dongling Xiao, Han Zhang, Yukun Li, Yu Sun, Hao Tian, Hua Wu, and Haifeng Wang. 2020. ERNIE-GEN: An Enhanced Multi-Flow Pre-training and Fine-tuning Framework for Natural Language Generation. arXiv preprint arXiv:2001.11314 (2020)."},{"key":"e_1_3_2_1_146_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1"},{"key":"e_1_3_2_1_147_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1"},{"key":"e_1_3_2_1_148_1","unstructured":"Linting Xue Noah Constant Adam Roberts Mihir Kale Rami Al-Rfou Aditya Siddhant Aditya Barua and Colin Raffel. 2020. mT5: A massively multilingual pre-trained text-to-text transformer. arXiv:2010.11934 [cs.CL]"},{"key":"e_1_3_2_1_149_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1"},{"key":"e_1_3_2_1_150_1","volume-title":"Xlnet: Generalized autoregressive pretraining for language understanding. In Advances in neural information processing systems. 5753--5763.","author":"Yang Zhilin","year":"2019","unstructured":"Zhilin Yang, Zihang Dai, Yiming Yang, Jaime Carbonell, Russ R Salakhutdinov, and Quoc V Le. 2019. Xlnet: Generalized autoregressive pretraining for language understanding. In Advances in neural information processing systems. 5753--5763."},{"key":"e_1_3_2_1_151_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1"},{"key":"e_1_3_2_1_152_1","volume-title":"Toward Inclusive Tech Policy Design: A Method for Underrepresented Voices to Strengthen Tech Policy Documents. Ethics and Information Technology","author":"Young Meg","year":"2019","unstructured":"Meg Young, Lassana Magassa, and Batya Friedman. 2019. Toward Inclusive Tech Policy Design: A Method for Underrepresented Voices to Strengthen Tech Policy Documents. Ethics and Information Technology (2019), 1--15."},{"key":"e_1_3_2_1_153_1","doi-asserted-by":"crossref","unstructured":"Ofir Zafrir Guy Boudoukh Peter Izsak and Moshe Wasserblat. 2019. Q8BERT: Quantized 8Bit BERT. arXiv:1910.06188 [cs.CL]","DOI":"10.1109\/EMC2-NIPS53020.2019.00016"},{"key":"e_1_3_2_1_154_1","doi-asserted-by":"publisher","DOI":"10.1145\/2460999.2461005"},{"key":"e_1_3_2_1_155_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1"},{"key":"e_1_3_2_1_156_1","doi-asserted-by":"publisher","DOI":"10.1145\/3368555.3384448"},{"key":"e_1_3_2_1_157_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1"},{"key":"e_1_3_2_1_158_1","doi-asserted-by":"publisher","DOI":"10.1162\/coli_a_00368"}],"event":{"name":"FAccT '21: 2021 ACM Conference on Fairness, Accountability, and Transparency","location":"Virtual Event Canada","acronym":"FAccT '21","sponsor":["ACM Association for Computing Machinery"]},"container-title":["Proceedings of the 2021 ACM Conference on Fairness, Accountability, and Transparency"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3442188.3445922","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3442188.3445922","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T20:48:57Z","timestamp":1750193337000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3442188.3445922"}},"subtitle":["Can Language Models Be Too Big? \ud83e\udd9c"],"short-title":[],"issued":{"date-parts":[[2021,3]]},"references-count":156,"alternative-id":["10.1145\/3442188.3445922","10.1145\/3442188"],"URL":"https:\/\/doi.org\/10.1145\/3442188.3445922","relation":{},"subject":[],"published":{"date-parts":[[2021,3]]},"assertion":[{"value":"2021-03-01","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}