{"type":"ScholarlyArticle","title":"WEFE: The Word Embeddings Fairness Evaluation Framework","authors":[{"name":"Pablo Badilla","slug":"pablo-badilla","given":"Pablo","family":"Badilla","affiliation":"Department of Computer Science , Universidad de Chile; Millennium Institute for Foundational Research on Data , IMFD-Chile"},{"name":"Felipe Bravo-Marquez","slug":"felipe-bravo-marquez","given":"Felipe","family":"Bravo-Marquez","affiliation":"Department of Computer Science , Universidad de Chile; Millennium Institute for Foundational Research on Data , IMFD-Chile"},{"name":"Jorge Pérez","slug":"jorge-perez","given":"Jorge","family":"Pérez","affiliation":"Department of Computer Science , Universidad de Chile; Millennium Institute for Foundational Research on Data , IMFD-Chile"}],"abstract":"Word embeddings are known to exhibit stereotypical biases towards gender, race, religion, among other criteria. Severa fairness metrics have been proposed in order to automatically quantify these biases. Although all metrics have a similar objective, the relationship between them is by no means clear. Two issues that prevent a clean comparison is that they operate with different inputs, and that their outputs are incompatible with each other. In this paper we propose WEFE, the word embeddings fairness evaluation framework, to encapsulate, evaluate and compare fairness metrics. Our framework needs a list of pre-trained embeddings and a set of fairness criteria, and it is based on checking correlations between fairness rankings induced by these criteria. We conduct a case study showing that rankings produced by existing fairness methods tend to correlate when measuring gender bias. This correlation is considerably less for other biases like race or religion. We also compare the fairness rankings with an embedding benchmark showing that there is no clear correlation between fairness and good performance in downstream tasks.","doi":"10.24963/ijcai.2020/60","url":"https://ijcai.org/proceedings/2020/60","pdf":"https://ijcai.org/proceedings/2020/0060.pdf","markdown":"https://ijcai.org/proceedings/2020/60.md","bibtex":"https://ijcai.org/proceedings/2020/bibtex/60","volume":{"slug":"2020","title":"Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2020","url":"https://ijcai.org/proceedings/2020/","year":2020,"location":"Yokohama","dates":"January 2021 (postponed from 11-17 July 2020)","editors":"Christian Bessiere","isbn":"978-0-9992411-6-5","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2020"},"section":"AI Ethics","track":"Main track","number":60,"pages":{"first":430,"last":436},"keywords":["Natural Language Processing: NLP Applications and Tools","Trust, Fairness, Bias: General","Natural Language Processing: Embeddings","AI Ethics: Fairness"],"videos":[{"label":"Video","url":"https://videos.ijcai20.org/24827/file_24827.m3u8","length_sec":291,"provider":"hls"}],"references":[{"position":1,"raw":"[Bojanowski et al., 2017] Piotr Bojanowski, Edouard Grave, Armand Joulin, and Tomas Mikolov. Enriching word vec- tors with subword information. Transactions of the Asso- ciation for Computational Linguistics, 5:135-146, 2017.","title":"Enriching word vectors with subword information","authors":"Piotr Bojanowski, Edouard Grave, Armand Joulin, Tomas Mikolov","year":"2017","venue":"Transactions of the Association for Computational Linguistics","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Bolukbasi et al., 2016] Tolga Bolukbasi, Kai-Wei Chang, James Y Zou, Venkatesh Saligrama, and Adam T Kalai. Man is to computer programmer as woman is to home- maker? debiasing word embeddings. In Advances in neural information processing systems, pages 4349-4357, 2016.","title":"Man is to computer programmer as woman is to homemaker? debiasing word embeddings","authors":"Tolga Bolukbasi, Kai-Wei Chang, James Y Zou, Venkatesh Saligrama, Adam T Kalai","year":"2016","venue":"Advances in neural information processing systems","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Caliskan et al., 2017] Aylin Caliskan, Joanna J Bryson, and Arvind Narayanan. Semantics derived automatically from language corpora contain human-like biases. Science, 356(6334):183-186, 2017.","title":"Semantics derived automatically from language corpora contain human-like biases","authors":"Aylin Caliskan, Joanna J Bryson, Arvind Narayanan","year":"2017","venue":"Science","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Ethayarajh et al., 2019] Kawin Ethayarajh, David Duve- naud, and Graeme Hirst. Understanding undesirable word embedding associations. In Proceedings of the 57th An- nual Meeting of the Association for Computational Lin- guistics, pages 1696-1705, Florence, Italy, July 2019. As- sociation for Computational Linguistics.","title":"Understanding undesirable word embedding associations","authors":"Kawin Ethayarajh, David Duvenaud, Graeme Hirst","year":"2019","venue":"Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Garg et al., 2018] Nikhil Garg, Londa Schiebinger, Dan Ju- rafsky, and James Zou. Word embeddings quantify 100 years of gender and ethnic stereotypes. Proceedings of the National Academy of Sciences, 115(16):E3635-E3644, 2018.","title":"Word embeddings quantify 100 years of gender and ethnic stereotypes","authors":"Nikhil Garg, Londa Schiebinger, Dan Jurafsky, James Zou","year":"2018","venue":"Proceedings of the National Academy of Sciences","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Goldberg, 2017] Yoav Goldberg. Neural network methods for natural language processing. Synthesis Lectures on Hu- man Language Technologies, 10(1):1-309, 2017.","title":"Neural network methods for natural language processing","authors":"Yoav Goldberg","year":"2017","venue":"Synthesis Lectures on Human Language Technologies","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Gonen and Goldberg, 2019] Hila Gonen and Yoav Gold- berg. Lipstick on a pig: Debiasing methods cover up systematic gender biases in word embeddings but do not remove them. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Com- putational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), pages 609-614, Min- neapolis, Minnesota, June 2019. Association for Compu- tational Linguistics.","title":"Lipstick on a pig: Debiasing methods cover up systematic gender biases in word embeddings but do not remove them","authors":"Gonen, Goldberg, Hila Gonen, Yoav Goldberg","year":"2019","venue":"Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Hu and Liu, 2004] Minqing Hu and Bing Liu. Mining and summarizing customer reviews. In Proceedings of the tenth ACM SIGKDD international conference on Knowl- edge discovery and data mining, pages 168-177. ACM, 2004.","title":"Mining and summarizing customer reviews","authors":"Liu Hu, Minqing Hu, Bing Liu","year":"2004","venue":"Proceedings of the tenth ACM SIGKDD international conference on Knowledge discovery and data mining","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Jastrzkebski et al., 2017] Stanislaw Jastrzkebski, Damian Lesniak, and Wojciech Marian Czarnecki. How to evaluate word embeddings? on importance of data efficiency and simple supervised tasks. CoRR, abs/1702.02170, 2017.","title":"How to evaluate word embeddings? on importance of data efficiency and simple supervised tasks","authors":"Jastrzkebski","year":"2017","venue":null,"doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Manzini et al., 2019] Thomas Manzini, Lim Yao Chong, Alan W Black, and Yulia Tsvetkov. Black is to criminal as caucasian is to police: Detecting and removing mul- ticlass bias in word embeddings. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Lan- guage Technologies, Volume 1 (Long and Short Papers), pages 615-621, Minneapolis, Minnesota, June 2019. As- sociation for Computational Linguistics. [Mikolov et al., 2013a] Tomas Mikolov, Kai Chen, Greg Corrado, and Jeffrey Dean. Efficient estimation of word representations in vector space. In 1st International Con- ference on Learning Representations, ICLR 2013, Scotts- dale, Arizona, USA, May 2-4, 2013, Workshop Track Pro- ceedings, 2013.","title":"Black is to criminal as caucasian is to police: Detecting and removing multiclass bias in word embeddings","authors":"Thomas Manzini, Lim Yao Chong, Alan W Black, Yulia Tsvetkov","year":"2013","venue":"Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Mikolov et al., 2013b] Tomas Mikolov, Ilya Sutskever, Kai Chen, Greg S Corrado, and Jeff Dean. Distributed repre- sentations of words and phrases and their compositional- ity. In Advances in neural information processing systems, pages 3111-3119, 2013.","title":"Distributed representations of words and phrases and their compositionality","authors":"Mikolov","year":"2013","venue":"Advances in neural information processing systems","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Pennington et al., 2014] Jeffrey Pennington, Richard Socher, and Christopher Manning. Glove: Global vectors for word representation. In Proceedings of the 2014 conference on empirical methods in natural language processing (EMNLP), pages 1532-1543, 2014.","title":"Glove: Global vectors for word representation","authors":"Jeffrey Pennington, Richard Socher, Christopher Manning","year":"2014","venue":"Proceedings of the 2014 conference on empirical methods in natural language processing (EMNLP)","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Salle et al., 2016] Alexandre Salle, Aline Villavicencio, and Marco Idiart. Matrix factorization using window sampling and negative sampling for improved word representations. In Proceedings of the 54th Annual Meeting of the Asso- ciation for Computational Linguistics (Volume 2: Short Papers), pages 419-424, Berlin, Germany, August 2016. Association for Computational Linguistics.","title":"Matrix factorization using window sampling and negative sampling for improved word representations","authors":"Alexandre Salle, Aline Villavicencio, Marco Idiart","year":"2016","venue":"Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Speer et al., 2017] Robyn Speer, Joshua Chin, and Cather- ine Havasi. ConceptNet 5.5: An open multilingual graph of general knowledge. pages 4444-4451, 2017.","title":"Robyn Speer","authors":"Speer","year":"2017","venue":"ConceptNet 5.5: An open multilingual graph of general knowledge","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Sweeney and Najafian, 2019] Chris Sweeney and Maryam Najafian. A transparent framework for evaluating unin- tended demographic bias in word embeddings. In Pro- ceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 1662-1667, 2019.","title":"A transparent framework for evaluating unintended demographic bias in word embeddings","authors":"Chris Sweeney, Maryam Najafian","year":"2019","venue":"Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Swinger et al., 2019] Nathaniel Swinger, Maria De- Arteaga, Neil Thomas Heffernan IV, Mark DM Leiserson, and Adam Tauman Kalai. What are the biases in my word embedding? In Proceedings of the 2019 AAAI/ACM Conference on AI, Ethics, and Society, pages 305-311, 2019.","title":"What are the biases in my word embedding?","authors":"Nathaniel Swinger, Maria De-Arteaga, Neil Thomas Heffernan, I V Mark Dm Leiserson, Adam Tauman, Kalai","year":"2019","venue":"Proceedings of the 2019 AAAI/ACM Conference on AI, Ethics, and Society","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Zhou et al., 2019] Pei Zhou, Weijia Shi, Jieyu Zhao, Kuan- Hao Huang, Muhao Chen, Ryan Cotterell, and Kai-Wei Chang. Examining gender bias in languages with gram- matical gender. In Proceedings of the 2019 Confer- ence on Empirical Methods in Natural Language Process- ing and the 9th International Joint Conference on Natu- ral Language Processing (EMNLP-IJCNLP), pages 5275- 5283, Hong Kong, China, November 2019. Association for Computational Linguistics.","title":"Examining gender bias in languages with grammatical gender","authors":"Pei Zhou, Weijia Shi, Jieyu Zhao, Kuan-Hao Huang, Muhao Chen, Ryan Cotterell, Kai-Wei Chang","year":"2019","venue":"Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}