{"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/phrase-based-neural-unsupervised-machine","title":"Phrase-Based & Neural Unsupervised Machine Translation","arxiv_id":"1804.07755","date":"2018-04-20","proceeding":"EMNLP 2018 10","authors":["Guillaume Lample","Myle Ott","Alexis Conneau","Ludovic Denoyer","Marc'Aurelio Ranzato"],"abstract":"Machine translation systems achieve near human-level performance on some\nlanguages, yet their effectiveness strongly relies on the availability of large\namounts of parallel sentences, which hinders their applicability to the\nmajority of language pairs. This work investigates how to learn to translate\nwhen having access to only large monolingual corpora in each language. We\npropose two model variants, a neural and a phrase-based model. Both versions\nleverage a careful initialization of the parameters, the denoising effect of\nlanguage models and automatic generation of parallel data by iterative\nback-translation. These models are significantly better than methods from the\nliterature, while being simpler and having fewer hyper-parameters. On the\nwidely used WMT'14 English-French and WMT'16 German-English benchmarks, our\nmodels respectively obtain 28.1 and 25.2 BLEU points without using a single\nparallel sentence, outperforming the state of the art by more than 11 BLEU\npoints. On low-resource languages like English-Urdu and English-Romanian, our\nmethods achieve even better results than semi-supervised and supervised\napproaches leveraging the paucity of available bitexts. Our code for NMT and\nPBSMT is publicly available.","url_abs":"http://arxiv.org/abs/1804.07755v2","url_pdf":"http://arxiv.org/pdf/1804.07755v2.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":"phrase-based-neural-unsupervised-machine","repo_url":"https://github.com/facebookresearch/UnsupervisedMT","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"phrase-based-neural-unsupervised-machine","repo_url":"https://github.com/1-punchMan/CLTS","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"phrase-based-neural-unsupervised-machine","repo_url":"https://github.com/Helsinki-NLP/shared-info","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"phrase-based-neural-unsupervised-machine","repo_url":"https://github.com/Kelechukwu1/PidginUNMT","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"phrase-based-neural-unsupervised-machine","repo_url":"https://github.com/deterministic-algorithms-lab/Large-XLM","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"phrase-based-neural-unsupervised-machine","repo_url":"https://github.com/facebookresearch/UnsupervisedQA","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"phrase-based-neural-unsupervised-machine","repo_url":"https://github.com/facebookresearch/XLM","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"phrase-based-neural-unsupervised-machine","repo_url":"https://github.com/feyzaakyurek/XLM-LwLL","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"phrase-based-neural-unsupervised-machine","repo_url":"https://github.com/fshdnc/enfi-XLM","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"phrase-based-neural-unsupervised-machine","repo_url":"https://github.com/keleog/PidginUNMT","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"phrase-based-neural-unsupervised-machine","repo_url":"https://github.com/kheeong/XLM_OWN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"phrase-based-neural-unsupervised-machine","repo_url":"https://github.com/luofuli/DualLanST","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"phrase-based-neural-unsupervised-machine","repo_url":"https://github.com/luofuli/DualRL","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"phrase-based-neural-unsupervised-machine","repo_url":"https://github.com/huggingface/transformers","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"machine-translation","task_name":"Machine Translation"},{"task_slug":"nmt","task_name":"NMT"},{"task_slug":"sentence","task_name":"Sentence"},{"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 PBSMT","rank_in_archive_order":52,"of":57,"metrics":{"BLEU score":"28.11"},"uses_additional_data":false},{"leaderboard":"/sota/machine-translation-on-wmt2014-english-french","task":"Machine Translation","dataset":"WMT2014 English-French","model":"PBSMT + NMT","rank_in_archive_order":53,"of":57,"metrics":{"BLEU score":"27.6"},"uses_additional_data":false},{"leaderboard":"/sota/machine-translation-on-wmt2014-english-french","task":"Machine Translation","dataset":"WMT2014 English-French","model":"Unsupervised NMT + Transformer","rank_in_archive_order":56,"of":57,"metrics":{"BLEU score":"25.14"},"uses_additional_data":false},{"leaderboard":"/sota/machine-translation-on-wmt2014-english-german","task":"Machine Translation","dataset":"WMT2014 English-German","model":"PBSMT + NMT","rank_in_archive_order":81,"of":91,"metrics":{"BLEU score":"20.23"},"uses_additional_data":false},{"leaderboard":"/sota/machine-translation-on-wmt2014-english-german","task":"Machine Translation","dataset":"WMT2014 English-German","model":"Unsupervised PBSMT","rank_in_archive_order":85,"of":91,"metrics":{"BLEU score":"17.94"},"uses_additional_data":false},{"leaderboard":"/sota/machine-translation-on-wmt2014-english-german","task":"Machine Translation","dataset":"WMT2014 English-German","model":"Unsupervised NMT + Transformer","rank_in_archive_order":87,"of":91,"metrics":{"BLEU score":"17.16"},"uses_additional_data":false},{"leaderboard":"/sota/machine-translation-on-wmt2016-english-1","task":"Machine Translation","dataset":"WMT2016 English-Romanian","model":"PBSMT + NMT","rank_in_archive_order":16,"of":21,"metrics":{"BLEU score":"25.13"},"uses_additional_data":false},{"leaderboard":"/sota/machine-translation-on-wmt2016-english-1","task":"Machine Translation","dataset":"WMT2016 English-Romanian","model":"Unsupervised PBSMT","rank_in_archive_order":17,"of":21,"metrics":{"BLEU score":"21.33"},"uses_additional_data":false},{"leaderboard":"/sota/machine-translation-on-wmt2016-english-1","task":"Machine Translation","dataset":"WMT2016 English-Romanian","model":"Unsupervised NMT + Transformer","rank_in_archive_order":18,"of":21,"metrics":{"BLEU score":"21.18"},"uses_additional_data":false},{"leaderboard":"/sota/machine-translation-on-wmt2016-english","task":"Machine Translation","dataset":"WMT2016 English-Russian","model":"PBSMT + NMT","rank_in_archive_order":2,"of":4,"metrics":{"BLEU score":"13.76"},"uses_additional_data":false},{"leaderboard":"/sota/machine-translation-on-wmt2016-english","task":"Machine Translation","dataset":"WMT2016 English-Russian","model":"Unsupervised PBSMT","rank_in_archive_order":3,"of":4,"metrics":{"BLEU score":"13.37"},"uses_additional_data":false},{"leaderboard":"/sota/machine-translation-on-wmt2016-english","task":"Machine Translation","dataset":"WMT2016 English-Russian","model":"Unsupervised NMT + Transformer","rank_in_archive_order":4,"of":4,"metrics":{"BLEU score":"7.98"},"uses_additional_data":false},{"leaderboard":"/sota/unsupervised-machine-translation-on-wmt2014-2","task":"Unsupervised Machine Translation","dataset":"WMT2014 English-French","model":"PBSMT + NMT","rank_in_archive_order":7,"of":7,"metrics":{"BLEU":"27.6"},"uses_additional_data":false},{"leaderboard":"/sota/unsupervised-machine-translation-on-wmt2014-1","task":"Unsupervised Machine Translation","dataset":"WMT2014 French-English","model":"PBSMT + NMT","rank_in_archive_order":6,"of":7,"metrics":{"BLEU":"27.7"},"uses_additional_data":false},{"leaderboard":"/sota/unsupervised-machine-translation-on-wmt2016","task":"Unsupervised Machine Translation","dataset":"WMT2016 English-German","model":"PBSMT + NMT","rank_in_archive_order":6,"of":7,"metrics":{"BLEU":"20.2"},"uses_additional_data":false},{"leaderboard":"/sota/unsupervised-machine-translation-on-wmt2016-1","task":"Unsupervised Machine Translation","dataset":"WMT2016 German-English","model":"PBSMT","rank_in_archive_order":7,"of":7,"metrics":{"BLEU":"25.2"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/1804.07755","atlas_url":"https://app.syntology.ai/?focus=1804.07755","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":"1804.07755"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1804.07755\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1804.07755"},"call":"get_concepts_for_paper(arxiv_id=\"1804.07755\")"}],"by_repo":[{"repo":"facebookresearch/UnsupervisedMT","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"1-punchMan/CLTS","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["1911.02116"],"harvested_for_calls":[{"arxiv_id":"1911.02116","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1911.02116"},"call":"get_harvested_code_for_paper(arxiv_id=\"1911.02116\")"}]},{"repo":"Helsinki-NLP/shared-info","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"Kelechukwu1/PidginUNMT","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"deterministic-algorithms-lab/Large-XLM","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["1911.02116"],"harvested_for_calls":[{"arxiv_id":"1911.02116","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1911.02116"},"call":"get_harvested_code_for_paper(arxiv_id=\"1911.02116\")"}]},{"repo":"facebookresearch/UnsupervisedQA","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"facebookresearch/XLM","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"feyzaakyurek/XLM-LwLL","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"fshdnc/enfi-XLM","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"keleog/PidginUNMT","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["1711.00043"],"harvested_for_calls":[{"arxiv_id":"1711.00043","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1711.00043"},"call":"get_harvested_code_for_paper(arxiv_id=\"1711.00043\")"}]},{"repo":"kheeong/XLM_OWN","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"luofuli/DualLanST","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["1905.10060"],"harvested_for_calls":[{"arxiv_id":"1905.10060","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1905.10060"},"call":"get_harvested_code_for_paper(arxiv_id=\"1905.10060\")"}]},{"repo":"luofuli/DualRL","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"huggingface/transformers","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":4,"harvested_for":["1706.03762","1910.03771","2006.03654","2010.01057"],"harvested_for_calls":[{"arxiv_id":"1706.03762","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1706.03762"},"call":"get_harvested_code_for_paper(arxiv_id=\"1706.03762\")"},{"arxiv_id":"1910.03771","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1910.03771"},"call":"get_harvested_code_for_paper(arxiv_id=\"1910.03771\")"},{"arxiv_id":"2006.03654","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2006.03654"},"call":"get_harvested_code_for_paper(arxiv_id=\"2006.03654\")"},{"arxiv_id":"2010.01057","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2010.01057"},"call":"get_harvested_code_for_paper(arxiv_id=\"2010.01057\")"}]}],"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":"f37099ac99f096857dba321f0d4b38bfc599a6b958bf1091c241bdcdc4e6da56","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}