{"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/towards-robust-and-privacy-preserving-text","title":"Towards Robust and Privacy-preserving Text Representations","arxiv_id":"1805.06093","date":"2018-05-16","proceeding":"ACL 2018 7","authors":["Yitong Li","Timothy Baldwin","Trevor Cohn"],"abstract":"Written text often provides sufficient clues to identify the author, their\ngender, age, and other important attributes. Consequently, the authorship of\ntraining and evaluation corpora can have unforeseen impacts, including\ndiffering model performance for different user groups, as well as privacy\nimplications. In this paper, we propose an approach to explicitly obscure\nimportant author characteristics at training time, such that representations\nlearned are invariant to these attributes. Evaluating on two tasks, we show\nthat this leads to increased privacy in the learned representations, as well as\nmore robust models to varying evaluation conditions, including out-of-domain\ncorpora.","url_abs":"http://arxiv.org/abs/1805.06093v1","url_pdf":"http://arxiv.org/pdf/1805.06093v1.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":"towards-robust-and-privacy-preserving-text","repo_url":"https://github.com/lrank/Robust_and_Privacy_preserving_Text_Representations","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"towards-robust-and-privacy-preserving-text","repo_url":"https://github.com/HanXudong/ReImplementation_Robust_and_Privacy_preserving_Text_Representations","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"towards-robust-and-privacy-preserving-text","repo_url":"https://github.com/anchit1704/PytorchReimplementation_Robust_and_Privacy_preserving_Text_Representations_KaggleNotebook","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"privacy-preserving","task_name":"Privacy Preserving"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1805.06093","atlas_url":"https://app.syntology.ai/?focus=1805.06093","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}