{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/gender-bias-in-coreference-resolution-1","title":"Gender Bias in Coreference Resolution: Evaluation and Debiasing Methods","arxiv_id":"1804.06876","date":"2018-04-18","proceeding":"NAACL 2018 6","authors":["Jieyu Zhao","Tianlu Wang","Mark Yatskar","Vicente Ordonez","Kai-Wei Chang"],"abstract":"We introduce a new benchmark, WinoBias, for coreference resolution focused on\ngender bias. Our corpus contains Winograd-schema style sentences with entities\ncorresponding to people referred by their occupation (e.g. the nurse, the\ndoctor, the carpenter). We demonstrate that a rule-based, a feature-rich, and a\nneural coreference system all link gendered pronouns to pro-stereotypical\nentities with higher accuracy than anti-stereotypical entities, by an average\ndifference of 21.1 in F1 score. Finally, we demonstrate a data-augmentation\napproach that, in combination with existing word-embedding debiasing\ntechniques, removes the bias demonstrated by these systems in WinoBias without\nsignificantly affecting their performance on existing coreference benchmark\ndatasets. Our dataset and code are available at http://winobias.org.","url_abs":"http://arxiv.org/abs/1804.06876v1","url_pdf":"http://arxiv.org/pdf/1804.06876v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"gender-bias-in-coreference-resolution-1","repo_url":"https://github.com/mapmeld/disambiguation_q","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"gender-bias-in-coreference-resolution-1","repo_url":"https://github.com/txsun1997/metric-fairness","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"gender-bias-in-coreference-resolution-1","repo_url":"https://github.com/uclanlp/corefBias","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"gender-bias-in-coreference-resolution-1","repo_url":"https://github.com/vergrig/RuBia-Dataset","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"CC-BY-4.0"}}],"tasks":[{"task_slug":"coreference-resolution","task_name":"Coreference Resolution"},{"task_slug":"data-augmentation","task_name":"Data Augmentation"},{"task_slug":"coreference-resolution-1","task_name":"coreference-resolution"}],"methods":[],"datasets_introduced":[{"slug":"winobias","name":"WinoBias","full_name":"WinoBias"}],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=1804.06876","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}