{"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-obfuscation-by-invariance","title":"Style Obfuscation by Invariance","arxiv_id":"1805.07143","date":"2018-05-18","proceeding":"COLING 2018 8","authors":["Chris Emmery","Enrique Manjavacas","Grzegorz Chrupała"],"abstract":"The task of obfuscating writing style using sequence models has previously\nbeen investigated under the framework of obfuscation-by-transfer, where the\ninput text is explicitly rewritten in another style. These approaches also\noften lead to major alterations to the semantic content of the input. In this\nwork, we propose obfuscation-by-invariance, and investigate to what extent\nmodels trained to be explicitly style-invariant preserve semantics. We evaluate\nour architectures on parallel and non-parallel corpora, and compare automatic\nand human evaluations on the obfuscated sentences. Our experiments show that\nstyle classifier performance can be reduced to chance level, whilst the\nautomatic evaluation of the output is seemingly equal to models applying\nstyle-transfer. However, based on human evaluation we demonstrate a trade-off\nbetween the level of obfuscation and the observed quality of the output in\nterms of meaning preservation and grammaticality.","url_abs":"http://arxiv.org/abs/1805.07143v1","url_pdf":"http://arxiv.org/pdf/1805.07143v1.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-obfuscation-by-invariance","repo_url":"https://github.com/cmry/style-obfuscation","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"style-transfer","task_name":"Style Transfer"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1805.07143","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}