{"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/unsupervised-neural-machine-translation-1","title":"Unsupervised Neural Machine Translation Initialized by Unsupervised Statistical Machine Translation","arxiv_id":"1810.12703","date":"2018-10-30","proceeding":null,"authors":["Benjamin Marie","Atsushi Fujita"],"abstract":"Recent work achieved remarkable results in training neural machine\ntranslation (NMT) systems in a fully unsupervised way, with new and dedicated\narchitectures that rely on monolingual corpora only. In this work, we propose\nto define unsupervised NMT (UNMT) as NMT trained with the supervision of\nsynthetic bilingual data. Our approach straightforwardly enables the use of\nstate-of-the-art architectures proposed for supervised NMT by replacing\nhuman-made bilingual data with synthetic bilingual data for training. We\npropose to initialize the training of UNMT with synthetic bilingual data\ngenerated by unsupervised statistical machine translation (USMT). The UNMT\nsystem is then incrementally improved using back-translation. Our preliminary\nexperiments show that our approach achieves a new state-of-the-art for\nunsupervised machine translation on the WMT16 German--English news translation\ntask, for both translation directions.","url_abs":"http://arxiv.org/abs/1810.12703v1","url_pdf":"http://arxiv.org/pdf/1810.12703v1.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":[],"tasks":[{"task_slug":"machine-translation","task_name":"Machine Translation"},{"task_slug":"nmt","task_name":"NMT"},{"task_slug":"translation","task_name":"Translation"},{"task_slug":"unsupervised-machine-translation","task_name":"Unsupervised Machine Translation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/unsupervised-machine-translation-on-wmt2016","task":"Unsupervised Machine Translation","dataset":"WMT2016 English-German","model":"Synthetic bilingual data init","rank_in_archive_order":7,"of":7,"metrics":{"BLEU":"20.0"},"uses_additional_data":false},{"leaderboard":"/sota/unsupervised-machine-translation-on-wmt2016-1","task":"Unsupervised Machine Translation","dataset":"WMT2016 German-English","model":"Synthetic bilingual data init","rank_in_archive_order":5,"of":7,"metrics":{"BLEU":"26.7"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1810.12703","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}