{"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/learning-gender-neutral-word-embeddings","title":"Learning Gender-Neutral Word Embeddings","arxiv_id":"1809.01496","date":"2018-08-29","proceeding":"EMNLP 2018 10","authors":["Jieyu Zhao","Yichao Zhou","Zeyu Li","Wei Wang","Kai-Wei Chang"],"abstract":"Word embedding models have become a fundamental component in a wide range of\nNatural Language Processing (NLP) applications. However, embeddings trained on\nhuman-generated corpora have been demonstrated to inherit strong gender\nstereotypes that reflect social constructs. To address this concern, in this\npaper, we propose a novel training procedure for learning gender-neutral word\nembeddings. Our approach aims to preserve gender information in certain\ndimensions of word vectors while compelling other dimensions to be free of\ngender influence. Based on the proposed method, we generate a Gender-Neutral\nvariant of GloVe (GN-GloVe). Quantitative and qualitative experiments\ndemonstrate that GN-GloVe successfully isolates gender information without\nsacrificing the functionality of the embedding model.","url_abs":"http://arxiv.org/abs/1809.01496v1","url_pdf":"http://arxiv.org/pdf/1809.01496v1.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":"learning-gender-neutral-word-embeddings","repo_url":"https://github.com/uclanlp/gn_glove","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"word-embeddings","task_name":"Word Embeddings"}],"methods":[{"method_slug":"glove","method_name":"GloVe"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1809.01496","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}