{"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/enhanced-neural-machine-translation-by","title":"Enhanced Neural Machine Translation by Learning from Draft","arxiv_id":"1710.01789","date":"2017-10-04","proceeding":null,"authors":["Aodong Li","Shiyue Zhang","Dong Wang","Thomas Fang Zheng"],"abstract":"Neural machine translation (NMT) has recently achieved impressive results. A\npotential problem of the existing NMT algorithm, however, is that the decoding\nis conducted from left to right, without considering the right context. This\npaper proposes an two-stage approach to solve the problem. In the first stage,\na conventional attention-based NMT system is used to produce a draft\ntranslation, and in the second stage, a novel double-attention NMT system is\nused to refine the translation, by looking at the original input as well as the\ndraft translation. This drafting-and-refinement can obtain the right-context\ninformation from the draft, hence producing more consistent translations. We\nevaluated this approach using two Chinese-English translation tasks, one with\n44k pairs and 1M pairs respectively. The experiments showed that our approach\nachieved positive improvements over the conventional NMT system: the\nimprovements are 2.4 and 0.9 BLEU points on the small-scale and large-scale\ntasks, respectively.","url_abs":"http://arxiv.org/abs/1710.01789v1","url_pdf":"http://arxiv.org/pdf/1710.01789v1.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":"enhanced-neural-machine-translation-by","repo_url":"https://github.com/aodongli/LearningFromDraft","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"enhanced-neural-machine-translation-by","repo_url":"https://github.com/aodongli/Learning_from_draft","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"machine-translation","task_name":"Machine Translation"},{"task_slug":"nmt","task_name":"NMT"},{"task_slug":"translation","task_name":"Translation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}