{"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/achieving-open-vocabulary-neural-machine","title":"Achieving Open Vocabulary Neural Machine Translation with Hybrid Word-Character Models","arxiv_id":"1604.00788","date":"2016-04-04","proceeding":"ACL 2016 8","authors":["Minh-Thang Luong","Christopher D. Manning"],"abstract":"Nearly all previous work on neural machine translation (NMT) has used quite\nrestricted vocabularies, perhaps with a subsequent method to patch in unknown\nwords. This paper presents a novel word-character solution to achieving open\nvocabulary NMT. We build hybrid systems that translate mostly at the word level\nand consult the character components for rare words. Our character-level\nrecurrent neural networks compute source word representations and recover\nunknown target words when needed. The twofold advantage of such a hybrid\napproach is that it is much faster and easier to train than character-based\nones; at the same time, it never produces unknown words as in the case of\nword-based models. On the WMT'15 English to Czech translation task, this hybrid\napproach offers an addition boost of +2.1-11.4 BLEU points over models that\nalready handle unknown words. Our best system achieves a new state-of-the-art\nresult with 20.7 BLEU score. We demonstrate that our character models can\nsuccessfully learn to not only generate well-formed words for Czech, a\nhighly-inflected language with a very complex vocabulary, but also build\ncorrect representations for English source words.","url_abs":"http://arxiv.org/abs/1604.00788v2","url_pdf":"http://arxiv.org/pdf/1604.00788v2.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":"achieving-open-vocabulary-neural-machine","repo_url":"https://github.com/Waino/hnmt","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"achieving-open-vocabulary-neural-machine","repo_url":"https://github.com/lmtoan/nlp-cs224n","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"achieving-open-vocabulary-neural-machine","repo_url":"https://github.com/yurayli/stanford-cs224n-sol","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"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":"https://app.syntology.ai/?focus=1604.00788","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1604.00788"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/yurayli/stanford-cs224n-sol","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Waino/hnmt","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/lmtoan/nlp-cs224n","reach":{"status":"ok"}}],"summary":{"ran_draft_wrong":2},"by_repo_kind":{"listed":{"samples":2,"ran":2,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":2,"samples":[{"code_sha256_prefix":"c9b519aed8c1c892","entry":"batch_budget","repo":"Waino/hnmt","repo_kind":"listed","path":"hnmt.py","file_url":"https://github.com/Waino/hnmt/blob/HEAD/hnmt.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"c9b519aed8c1c892"}},{"code_sha256_prefix":"94e0944c2b466a91","entry":"detokenize","repo":"Waino/hnmt","repo_kind":"listed","path":"hnmt.py","file_url":"https://github.com/Waino/hnmt/blob/HEAD/hnmt.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"94e0944c2b466a91"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}