{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"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":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers","held":null,"reason":"arxiv_id_not_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"by_repo":[{"repo":"aodongli/LearningFromDraft","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"aodongli/Learning_from_draft","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0}],"by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"b816b908b4e2b68120158e3a342f0f956839b78686c9dec808a7a2d10c792f5c","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}