{"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/non-adversarial-unsupervised-word-translation","title":"Non-Adversarial Unsupervised Word Translation","arxiv_id":"1801.06126","date":"2018-01-18","proceeding":"EMNLP 2018 10","authors":["Yedid Hoshen","Lior Wolf"],"abstract":"Unsupervised word translation from non-parallel inter-lingual corpora has\nattracted much research interest. Very recently, neural network methods trained\nwith adversarial loss functions achieved high accuracy on this task. Despite\nthe impressive success of the recent techniques, they suffer from the typical\ndrawbacks of generative adversarial models: sensitivity to hyper-parameters,\nlong training time and lack of interpretability. In this paper, we make the\nobservation that two sufficiently similar distributions can be aligned\ncorrectly with iterative matching methods. We present a novel method that first\naligns the second moment of the word distributions of the two languages and\nthen iteratively refines the alignment. Extensive experiments on word\ntranslation of European and Non-European languages show that our method\nachieves better performance than recent state-of-the-art deep adversarial\napproaches and is competitive with the supervised baseline. It is also\nefficient, easy to parallelize on CPU and interpretable.","url_abs":"http://arxiv.org/abs/1801.06126v3","url_pdf":"http://arxiv.org/pdf/1801.06126v3.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":"non-adversarial-unsupervised-word-translation","repo_url":"https://github.com/facebookresearch/MUSE","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"non-adversarial-unsupervised-word-translation","repo_url":"https://github.com/facebookresearch/Non-adversarialTranslation","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"non-adversarial-unsupervised-word-translation","repo_url":"https://github.com/grtzsohalf/Audio-Phonetic-and-Semantic-Embedding","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"non-adversarial-unsupervised-word-translation","repo_url":"https://github.com/jiajunhua/facebookresearch-MUSE","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}}],"tasks":[{"task_slug":null,"task_name":"CPU"},{"task_slug":"translation","task_name":"Translation"},{"task_slug":"word-translation","task_name":"Word Translation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1801.06126","atlas_url":"https://app.syntology.ai/?focus=1801.06126","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":"1801.06126"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1801.06126\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1801.06126"},"call":"get_concepts_for_paper(arxiv_id=\"1801.06126\")"}],"by_repo":[{"repo":"facebookresearch/MUSE","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2305.14189"],"harvested_for_calls":[{"arxiv_id":"2305.14189","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2305.14189"},"call":"get_harvested_code_for_paper(arxiv_id=\"2305.14189\")"}]},{"repo":"facebookresearch/Non-adversarialTranslation","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"grtzsohalf/Audio-Phonetic-and-Semantic-Embedding","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"jiajunhua/facebookresearch-MUSE","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":"cfeaf34fe6d8999aeabe3d0636bb9f0594771f30d6cc400a6773ae5387d1ba47","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}