{"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/unsupervised-statistical-machine-translation","title":"Unsupervised Statistical Machine Translation","arxiv_id":"1809.01272","date":"2018-09-04","proceeding":"EMNLP 2018 10","authors":["Mikel Artetxe","Gorka Labaka","Eneko Agirre"],"abstract":"While modern machine translation has relied on large parallel corpora, a\nrecent line of work has managed to train Neural Machine Translation (NMT)\nsystems from monolingual corpora only (Artetxe et al., 2018c; Lample et al.,\n2018). Despite the potential of this approach for low-resource settings,\nexisting systems are far behind their supervised counterparts, limiting their\npractical interest. In this paper, we propose an alternative approach based on\nphrase-based Statistical Machine Translation (SMT) that significantly closes\nthe gap with supervised systems. Our method profits from the modular\narchitecture of SMT: we first induce a phrase table from monolingual corpora\nthrough cross-lingual embedding mappings, combine it with an n-gram language\nmodel, and fine-tune hyperparameters through an unsupervised MERT variant. In\naddition, iterative backtranslation improves results further, yielding, for\ninstance, 14.08 and 26.22 BLEU points in WMT 2014 English-German and\nEnglish-French, respectively, an improvement of more than 7-10 BLEU points over\nprevious unsupervised systems, and closing the gap with supervised SMT (Moses\ntrained on Europarl) down to 2-5 BLEU points. Our implementation is available\nat https://github.com/artetxem/monoses","url_abs":"http://arxiv.org/abs/1809.01272v1","url_pdf":"http://arxiv.org/pdf/1809.01272v1.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-statistical-machine-translation","repo_url":"https://github.com/artetxem/monoses","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"GPL-3.0"}},{"paper_slug":"unsupervised-statistical-machine-translation","repo_url":"https://github.com/artetxem/vecmap","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null},{"paper_slug":"unsupervised-statistical-machine-translation","repo_url":"https://github.com/artetxem/phrase2vec","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"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":"SMT + iterative backtranslation (unsupervised)","rank_in_archive_order":55,"of":57,"metrics":{"BLEU score":"26.22"},"uses_additional_data":false},{"leaderboard":"/sota/machine-translation-on-wmt2014-english-german","task":"Machine Translation","dataset":"WMT2014 English-German","model":"SMT + iterative backtranslation (unsupervised)","rank_in_archive_order":88,"of":91,"metrics":{"BLEU score":"14.08"},"uses_additional_data":false},{"leaderboard":"/sota/machine-translation-on-wmt2014-french-english","task":"Machine Translation","dataset":"WMT2014 French-English","model":"SMT + iterative backtranslation (unsupervised)","rank_in_archive_order":3,"of":3,"metrics":{"BLEU score":"25.87"},"uses_additional_data":false},{"leaderboard":"/sota/machine-translation-on-wmt2014-german-english","task":"Machine Translation","dataset":"WMT2014 German-English","model":"SMT + iterative backtranslation (unsupervised)","rank_in_archive_order":16,"of":16,"metrics":{"BLEU score":"17.43"},"uses_additional_data":false},{"leaderboard":"/sota/machine-translation-on-wmt2016-english-german","task":"Machine Translation","dataset":"WMT2016 English-German","model":"SMT + iterative backtranslation (unsupervised)","rank_in_archive_order":9,"of":12,"metrics":{"BLEU score":" 18.23"},"uses_additional_data":false},{"leaderboard":"/sota/machine-translation-on-wmt2016-german-english","task":"Machine Translation","dataset":"WMT2016 German-English","model":"SMT + iterative backtranslation (unsupervised)","rank_in_archive_order":5,"of":8,"metrics":{"BLEU score":"23.05"},"uses_additional_data":false},{"leaderboard":"/sota/unsupervised-machine-translation-on-wmt2014-1","task":"Unsupervised Machine Translation","dataset":"WMT2014 French-English","model":"SMT","rank_in_archive_order":7,"of":7,"metrics":{"BLEU":"25.9"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/1809.01272","atlas_url":"https://app.syntology.ai/?focus=1809.01272","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"1809.01272"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1809.01272\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1809.01272"},"call":"get_concepts_for_paper(arxiv_id=\"1809.01272\")"}],"by_repo":[{"repo":"artetxem/monoses","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"artetxem/vecmap","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2204.08887"],"harvested_for_calls":[{"arxiv_id":"2204.08887","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2204.08887"},"call":"get_harvested_code_for_paper(arxiv_id=\"2204.08887\")"}]},{"repo":"artetxem/phrase2vec","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0}],"by_repo_harvested_for_is":"harvested_for: the arXiv ids (as Syntology's graph holds them) of every paper whose samples Syntology's graph links to this repository, in arXiv-id order, complete; the page names the first 3 and says how many more. A link only: it does not say the papers are the same work, that one copied the other, or that the code implements this paper's method; harvested_for_calls gives the get_harvested_code_for_paper call for each arXiv-shaped id among them","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":"1f53ead5fb4d93eb211b903956c025c3929adb20e4a28ebd9a4eb7ae07db36db","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}