{"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/extreme-adaptation-for-personalized-neural","title":"Extreme Adaptation for Personalized Neural Machine Translation","arxiv_id":"1805.01817","date":"2018-05-04","proceeding":"ACL 2018 7","authors":["Paul Michel","Graham Neubig"],"abstract":"Every person speaks or writes their own flavor of their native language,\ninfluenced by a number of factors: the content they tend to talk about, their\ngender, their social status, or their geographical origin.\n  When attempting to perform Machine Translation (MT), these variations have a\nsignificant effect on how the system should perform translation, but this is\nnot captured well by standard one-size-fits-all models.\n  In this paper, we propose a simple and parameter-efficient adaptation\ntechnique that only requires adapting the bias of the output softmax to each\nparticular user of the MT system, either directly or through a factored\napproximation.\n  Experiments on TED talks in three languages demonstrate improvements in\ntranslation accuracy, and better reflection of speaker traits in the target\ntext.","url_abs":"http://arxiv.org/abs/1805.01817v1","url_pdf":"http://arxiv.org/pdf/1805.01817v1.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":"extreme-adaptation-for-personalized-neural","repo_url":"https://github.com/neulab/extreme-adaptation-for-personalized-translation","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"machine-translation","task_name":"Machine Translation"},{"task_slug":"translation","task_name":"Translation"}],"methods":[{"method_slug":"softmax","method_name":"Softmax"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1805.01817","atlas_url":"https://app.syntology.ai/?focus=1805.01817","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}