{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T04:25:15Z","timestamp":1750220715925,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":34,"publisher":"ACM","license":[{"start":{"date-parts":[[2020,4,25]],"date-time":"2020-04-25T00:00:00Z","timestamp":1587772800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2020,4,25]]},"DOI":"10.1145\/3334480.3382949","type":"proceedings-article","created":{"date-parts":[[2020,5,28]],"date-time":"2020-05-28T12:52:32Z","timestamp":1590670352000},"page":"1-9","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":4,"title":["A General Methodology to Quantify Biases in Natural Language Data"],"prefix":"10.1145","author":[{"given":"Jiawei","family":"Chen","sequence":"first","affiliation":[{"name":"Google, Mountain View, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Anbang","family":"Xu","sequence":"additional","affiliation":[{"name":"IBM Almaden Research Center, San Jose, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhe","family":"Liu","sequence":"additional","affiliation":[{"name":"IBM Almaden Research Center, San Jose, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yufan","family":"Guo","sequence":"additional","affiliation":[{"name":"IBM Almaden Research Center, San Jose, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaotong","family":"Liu","sequence":"additional","affiliation":[{"name":"IBM Almaden Research Center, San Jose, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yingbei","family":"Tong","sequence":"additional","affiliation":[{"name":"IBM Almaden Research Center, San Jose, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rama","family":"Akkiraju","sequence":"additional","affiliation":[{"name":"IBM Almaden Research Center, San Jose, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"John M.","family":"Carroll","sequence":"additional","affiliation":[{"name":"Pennsylvania State University, University Park, PA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2020,4,25]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"Tolga Bolukbasi Kai-Wei Chang James Y Zou Venkatesh Saligrama and Adam T Kalai. 2016. Man is to computer programmer as woman is to homemaker? debiasing word embeddings. In Advances in Neural Information Processing Systems. 4349--4357."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/HICSS.2010.412"},{"key":"e_1_3_2_1_3_1","volume-title":"Semantics derived automatically from language corpora necessarily contain human biases. arXiv preprint arXiv:1608.07187","author":"Caliskan-Islam Aylin","year":"2016","unstructured":"Aylin Caliskan-Islam, Joanna J Bryson, and Arvind Narayanan. 2016. Semantics derived automatically from language corpora necessarily contain human biases. arXiv preprint arXiv:1608.07187 (2016), 1--14."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/2578726.2578729"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.2307\/1229039"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-67217-5_10"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/1753326.1753504"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/3173574.3173986"},{"key":"e_1_3_2_1_9_1","volume-title":"Proceedings of the Eighth International Joint Conference on Natural Language Processing (Volume 1: Long Papers)","volume":"1","author":"Gao Lei","year":"2017","unstructured":"Lei Gao, Alexis Kuppersmith, and Ruihong Huang. 2017. Recognizing Explicit and Implicit Hate Speech Using a Weakly Supervised Two-path Bootstrapping Approach. In Proceedings of the Eighth International Joint Conference on Natural Language Processing (Volume 1: Long Papers), Vol. 1. 774--782."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1720347115"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/1978942.1979106"},{"key":"e_1_3_2_1_12_1","volume-title":"Bias: A CBS insider exposes how the media distort the news","author":"Goldberg Bernard","year":"2014","unstructured":"Bernard Goldberg. 2014. Bias: A CBS insider exposes how the media distort the news. Regnery Publishing."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.5555\/3176748.3176757"},{"key":"e_1_3_2_1_14_1","unstructured":"Jacob Goldberger Geoffrey E Hinton Sam T Roweis and Ruslan R Salakhutdinov. 2005. Neighbourhood components analysis. In Advances in neural information processing systems. 513--520."},{"key":"e_1_3_2_1_15_1","volume-title":"Journal of Machine Learning Research","author":"Gretton Arthur","year":"2012","unstructured":"Arthur Gretton, Karsten M Borgwardt, Malte J Rasch, Bernhard Sch\u00f6lkopf, and Alexander Smola. 2012. A kernel two-sample test. Journal of Machine Learning Research 13, Mar (2012), 723--773."},{"key":"e_1_3_2_1_16_1","volume-title":"Toward Controlled Generation of Text. In International Conference on Machine Learning. 1587--1596","author":"Hu Zhiting","year":"2017","unstructured":"Zhiting Hu, Zichao Yang, Xiaodan Liang, Ruslan Salakhutdinov, and Eric P Xing. 2017. Toward Controlled Generation of Text. In International Conference on Machine Learning. 1587--1596."},{"key":"e_1_3_2_1_17_1","volume-title":"Visualizing and understanding recurrent networks. arXiv preprint arXiv:1506.02078","author":"Karpathy Andrej","year":"2015","unstructured":"Andrej Karpathy, Justin Johnson, and Li Fei-Fei. 2015. Visualizing and understanding recurrent networks. arXiv preprint arXiv:1506.02078 (2015)."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/2702123.2702520"},{"key":"e_1_3_2_1_19_1","volume-title":"Ying Zhang, Saizheng Zhang, Aaron C Courville, and Yoshua Bengio.","author":"Lamb Alex M","year":"2016","unstructured":"Alex M Lamb, Anirudh Goyal ALIAS PARTH GOYAL, Ying Zhang, Saizheng Zhang, Aaron C Courville, and Yoshua Bengio. 2016. Professor forcing: A new algorithm for training recurrent networks. In Advances In Neural Information Processing Systems. 4601--4609."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-1169"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/2858036.2858422"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/2631775.2631788"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-13734-6_25"},{"key":"e_1_3_2_1_24_1","unstructured":"Tomas Mikolov Ilya Sutskever Kai Chen Greg S Corrado and Jeff Dean. 2013. Distributed representations of words and phrases and their compositionality. In Advances in neural information processing systems. 3111--3119."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1080\/10463280701489053"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/1518701.1518772"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/IRI.2017.73"},{"key":"e_1_3_2_1_28_1","volume-title":"Stochastic Backpropagation and Approximate Inference in Deep Generative Models. In International Conference on Machine Learning. 1278--1286","author":"Rezende Danilo Jimenez","year":"2014","unstructured":"Danilo Jimenez Rezende, Shakir Mohamed, and Daan Wierstra. 2014. Stochastic Backpropagation and Approximate Inference in Deep Generative Models. In International Conference on Machine Learning. 1278--1286."},{"key":"e_1_3_2_1_29_1","unstructured":"Tianxiao Shen Tao Lei Regina Barzilay and Tommi Jaakkola. 2017. Style transfer from non-parallel text by cross-alignment. In Advances in Neural Information Processing Systems. 6830--6841."},{"key":"e_1_3_2_1_30_1","volume-title":"Generative models and model criticism via optimized maximum mean discrepancy. arXiv preprint arXiv:1611.04488","author":"Sutherland Dougal J","year":"2016","unstructured":"Dougal J Sutherland, Hsiao-Yu Tung, Heiko Strathmann, Soumyajit De, Aaditya Ramdas, Alex Smola, and Arthur Gretton. 2016. Generative models and model criticism via optimized maximum mean discrepancy. arXiv preprint arXiv:1611.04488 (2016)."},{"key":"e_1_3_2_1_31_1","volume-title":"Proceedings of the 50th Annual Meeting of the Association for Computational Linguistics: Short Papers-Volume 2. Association for Computational Linguistics, 90--94","author":"Wang Sida","year":"2012","unstructured":"Sida Wang and Christopher D Manning. 2012. Baselines and bigrams: Simple, good sentiment and topic classification. In Proceedings of the 50th Annual Meeting of the Association for Computational Linguistics: Short Papers-Volume 2. Association for Computational Linguistics, 90--94."},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1177\/1081180X07299804"},{"key":"e_1_3_2_1_33_1","volume-title":"B-test: A non-parametric, low variance kernel two-sample test. In Advances in neural information processing systems. 755--763.","author":"Zaremba Wojciech","year":"2013","unstructured":"Wojciech Zaremba, Arthur Gretton, and Matthew Blaschko. 2013. B-test: A non-parametric, low variance kernel two-sample test. In Advances in neural information processing systems. 755--763."},{"key":"e_1_3_2_1_34_1","volume-title":"Adversarially regularized autoencoders for generating discrete structures. CoRR, abs\/1706.04223","author":"Zhao Junbo Jake","year":"2017","unstructured":"Junbo Jake Zhao, Yoon Kim, Kelly Zhang, Alexander M Rush, and Yann LeCun. 2017. Adversarially regularized autoencoders for generating discrete structures. CoRR, abs\/1706.04223 (2017)."}],"event":{"name":"CHI '20: CHI Conference on Human Factors in Computing Systems","sponsor":["SIGCHI ACM Special Interest Group on Computer-Human Interaction"],"location":"Honolulu HI USA","acronym":"CHI '20"},"container-title":["Extended Abstracts of the 2020 CHI Conference on Human Factors in Computing Systems"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3334480.3382949","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3334480.3382949","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T22:33:21Z","timestamp":1750199601000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3334480.3382949"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,4,25]]},"references-count":34,"alternative-id":["10.1145\/3334480.3382949","10.1145\/3334480"],"URL":"https:\/\/doi.org\/10.1145\/3334480.3382949","relation":{},"subject":[],"published":{"date-parts":[[2020,4,25]]},"assertion":[{"value":"2020-04-25","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}