{"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","title":"Unsupervised Neural Machine Translation","arxiv_id":"1710.11041","date":"2017-10-30","proceeding":"ICLR 2018 1","authors":["Mikel Artetxe","Gorka Labaka","Eneko Agirre","Kyunghyun Cho"],"abstract":"In spite of the recent success of neural machine translation (NMT) in\nstandard benchmarks, the lack of large parallel corpora poses a major practical\nproblem for many language pairs. There have been several proposals to alleviate\nthis issue with, for instance, triangulation and semi-supervised learning\ntechniques, but they still require a strong cross-lingual signal. In this work,\nwe completely remove the need of parallel data and propose a novel method to\ntrain an NMT system in a completely unsupervised manner, relying on nothing but\nmonolingual corpora. Our model builds upon the recent work on unsupervised\nembedding mappings, and consists of a slightly modified attentional\nencoder-decoder model that can be trained on monolingual corpora alone using a\ncombination of denoising and backtranslation. Despite the simplicity of the\napproach, our system obtains 15.56 and 10.21 BLEU points in WMT 2014\nFrench-to-English and German-to-English translation. The model can also profit\nfrom small parallel corpora, and attains 21.81 and 15.24 points when combined\nwith 100,000 parallel sentences, respectively. Our implementation is released\nas an open source project.","url_abs":"http://arxiv.org/abs/1710.11041v2","url_pdf":"http://arxiv.org/pdf/1710.11041v2.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":"unsupervised-neural-machine-translation","repo_url":"https://github.com/artetxem/undreamt","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"GPL-3.0"}},{"paper_slug":"unsupervised-neural-machine-translation","repo_url":"https://github.com/rsennrich/subword-nmt","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"decoder","task_name":"Decoder"},{"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/machine-translation-on-wmt2014-english-french","task":"Machine Translation","dataset":"WMT2014 English-French","model":"Unsupervised attentional encoder-decoder + BPE","rank_in_archive_order":57,"of":57,"metrics":{"BLEU score":"14.36"},"uses_additional_data":false},{"leaderboard":"/sota/machine-translation-on-wmt2015-english-german","task":"Machine Translation","dataset":"WMT2015 English-German","model":"Unsupervised attentional encoder-decoder + BPE","rank_in_archive_order":6,"of":6,"metrics":{"BLEU score":"6.89"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/1710.11041","atlas_url":"https://app.syntology.ai/?focus=1710.11041","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1710.11041"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/artetxem/undreamt","reach":{"status":"ok","spdx":"GPL-3.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/rsennrich/subword-nmt","reach":null}],"summary":{"ran_violates":1,"ran_draft_wrong":4,"ran_fixture":1},"by_repo_kind":{},"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":6,"samples":[{"code_sha256_prefix":"a0deb98db94ae939","entry":"check_vocab_and_split","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"a0deb98db94ae939"}},{"code_sha256_prefix":"1dc5d59fd80a7419","entry":"create_parser","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"1dc5d59fd80a7419"}},{"code_sha256_prefix":"f9d4ba98fc7a6214","entry":"create_parser","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"f9d4ba98fc7a6214"}},{"code_sha256_prefix":"932ffa4dce8fc503","entry":"encode","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"932ffa4dce8fc503"}},{"code_sha256_prefix":"fe96394f96a9c638","entry":"get_pair_statistics","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"fe96394f96a9c638"}},{"code_sha256_prefix":"b83d785ca99bfc9f","entry":"get_vocabulary","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"b83d785ca99bfc9f"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}