{"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/style-transfer-through-back-translation","title":"Style Transfer Through Back-Translation","arxiv_id":"1804.09000","date":"2018-04-24","proceeding":"ACL 2018 7","authors":["Shrimai Prabhumoye","Yulia Tsvetkov","Ruslan Salakhutdinov","Alan W. black"],"abstract":"Style transfer is the task of rephrasing the text to contain specific\nstylistic properties without changing the intent or affect within the context.\nThis paper introduces a new method for automatic style transfer. We first learn\na latent representation of the input sentence which is grounded in a language\ntranslation model in order to better preserve the meaning of the sentence while\nreducing stylistic properties. Then adversarial generation techniques are used\nto make the output match the desired style. We evaluate this technique on three\ndifferent style transformations: sentiment, gender and political slant.\nCompared to two state-of-the-art style transfer modeling techniques we show\nimprovements both in automatic evaluation of style transfer and in manual\nevaluation of meaning preservation and fluency.","url_abs":"http://arxiv.org/abs/1804.09000v3","url_pdf":"http://arxiv.org/pdf/1804.09000v3.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":"style-transfer-through-back-translation","repo_url":"https://github.com/shrimai/Style-Transfer-Through-Back-Translation","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"style-transfer-through-back-translation","repo_url":"https://github.com/avshalomc/subtract","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"style-transfer-through-back-translation","repo_url":"https://github.com/namanphy/style-transfer-through-back-translate","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"sentence","task_name":"Sentence"},{"task_slug":"style-transfer","task_name":"Style Transfer"},{"task_slug":"text-style-transfoer","task_name":"Text Style Transfer"},{"task_slug":"translation","task_name":"Translation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1804.09000","atlas_url":"https://app.syntology.ai/?focus=1804.09000","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}