{"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/attenuating-bias-in-word-vectors","title":"Attenuating Bias in Word Vectors","arxiv_id":"1901.07656","date":"2019-01-23","proceeding":null,"authors":["Sunipa Dev","Jeff Phillips"],"abstract":"Word vector representations are well developed tools for various NLP and\nMachine Learning tasks and are known to retain significant semantic and\nsyntactic structure of languages. But they are prone to carrying and amplifying\nbias which can perpetrate discrimination in various applications. In this work,\nwe explore new simple ways to detect the most stereotypically gendered words in\nan embedding and remove the bias from them. We verify how names are masked\ncarriers of gender bias and then use that as a tool to attenuate bias in\nembeddings. Further, we extend this property of names to show how names can be\nused to detect other types of bias in the embeddings such as bias based on\nrace, ethnicity, and age.","url_abs":"http://arxiv.org/abs/1901.07656v1","url_pdf":"http://arxiv.org/pdf/1901.07656v1.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":"attenuating-bias-in-word-vectors","repo_url":"https://github.com/sunipa/Attenuating-Bias-in-Word-Vec","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1901.07656","atlas_url":"https://app.syntology.ai/?focus=1901.07656","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}