{"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/mind-the-gap-a-balanced-corpus-of-gendered","title":"Mind the GAP: A Balanced Corpus of Gendered Ambiguous Pronouns","arxiv_id":"1810.05201","date":"2018-10-11","proceeding":"TACL 2018 1","authors":["Kellie Webster","Marta Recasens","Vera Axelrod","Jason Baldridge"],"abstract":"Coreference resolution is an important task for natural language\nunderstanding, and the resolution of ambiguous pronouns a longstanding\nchallenge. Nonetheless, existing corpora do not capture ambiguous pronouns in\nsufficient volume or diversity to accurately indicate the practical utility of\nmodels. Furthermore, we find gender bias in existing corpora and systems\nfavoring masculine entities. To address this, we present and release GAP, a\ngender-balanced labeled corpus of 8,908 ambiguous pronoun-name pairs sampled to\nprovide diverse coverage of challenges posed by real-world text. We explore a\nrange of baselines which demonstrate the complexity of the challenge, the best\nachieving just 66.9% F1. We show that syntactic structure and continuous neural\nmodels provide promising, complementary cues for approaching the challenge.","url_abs":"http://arxiv.org/abs/1810.05201v1","url_pdf":"http://arxiv.org/pdf/1810.05201v1.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":"mind-the-gap-a-balanced-corpus-of-gendered","repo_url":"https://github.com/Yorko/gender-unbiased_BERT-based_pronoun_resolution","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"mind-the-gap-a-balanced-corpus-of-gendered","repo_url":"https://github.com/google-research-datasets/gap-coreference","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"mind-the-gap-a-balanced-corpus-of-gendered","repo_url":"https://github.com/sattree/gpr_pub","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"mind-the-gap-a-balanced-corpus-of-gendered","repo_url":"https://github.com/vid-koci/weightingGAP","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"coreference-resolution","task_name":"Coreference Resolution"},{"task_slug":"diversity","task_name":"Diversity"},{"task_slug":"natural-language-understanding","task_name":"Natural Language Understanding"}],"methods":[],"datasets_introduced":[{"slug":"gap-coreference-dataset","name":"GAP Coreference Dataset","full_name":""}],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}