{"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/generating-clues-for-gender-based-occupation","title":"Generating Clues for Gender based Occupation De-biasing in Text","arxiv_id":"1804.03839","date":"2018-04-11","proceeding":null,"authors":["Nishtha Madaan","Gautam Singh","Sameep Mehta","Aditya Chetan","Brihi Joshi"],"abstract":"Vast availability of text data has enabled widespread training and use of AI\nsystems that not only learn and predict attributes from the text but also\ngenerate text automatically. However, these AI models also learn gender, racial\nand ethnic biases present in the training data. In this paper, we present the\nfirst system that discovers the possibility that a given text portrays a gender\nstereotype associated with an occupation. If the possibility exists, the system\noffers counter-evidences of opposite gender also being associated with the same\noccupation in the context of user-provided geography and timespan. The system\nthus enables text de-biasing by assisting a human-in-the-loop. The system can\nnot only act as a text pre-processor before training any AI model but also help\nhuman story writers write stories free of occupation-level gender bias in the\ngeographical and temporal context of their choice.","url_abs":"http://arxiv.org/abs/1804.03839v1","url_pdf":"http://arxiv.org/pdf/1804.03839v1.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":"generating-clues-for-gender-based-occupation","repo_url":"https://github.com/nishthaa/occupation-debiasing","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1804.03839","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}