{"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-neural-machine-translation-with-1","title":"Unsupervised Neural Machine Translation with Weight Sharing","arxiv_id":"1804.09057","date":"2018-04-24","proceeding":"ACL 2018 7","authors":["Zhen Yang","Wei Chen","Feng Wang","Bo Xu"],"abstract":"Unsupervised neural machine translation (NMT) is a recently proposed approach\nfor machine translation which aims to train the model without using any labeled\ndata. The models proposed for unsupervised NMT often use only one shared\nencoder to map the pairs of sentences from different languages to a\nshared-latent space, which is weak in keeping the unique and internal\ncharacteristics of each language, such as the style, terminology, and sentence\nstructure. To address this issue, we introduce an extension by utilizing two\nindependent encoders but sharing some partial weights which are responsible for\nextracting high-level representations of the input sentences. Besides, two\ndifferent generative adversarial networks (GANs), namely the local GAN and\nglobal GAN, are proposed to enhance the cross-language translation. With this\nnew approach, we achieve significant improvements on English-German,\nEnglish-French and Chinese-to-English translation tasks.","url_abs":"http://arxiv.org/abs/1804.09057v1","url_pdf":"http://arxiv.org/pdf/1804.09057v1.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-with-1","repo_url":"https://github.com/ZhenYangIACAS/unsupervised-NMT","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":{"status":"ok"}}],"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"}],"methods":[{"method_slug":"convolution","method_name":"Convolution"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/machine-translation-on-wmt2016-english-german","task":"Machine Translation","dataset":"WMT2016 English-German","model":"Unsupervised NMT + weight-sharing","rank_in_archive_order":10,"of":12,"metrics":{"BLEU score":"10.86"},"uses_additional_data":false},{"leaderboard":"/sota/machine-translation-on-wmt2016-german-english","task":"Machine Translation","dataset":"WMT2016 German-English","model":"Unsupervised NMT + weight-sharing","rank_in_archive_order":6,"of":8,"metrics":{"BLEU score":"14.62"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/1804.09057","atlas_url":"https://app.syntology.ai/?focus=1804.09057","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":"1804.09057"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1804.09057\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1804.09057"},"call":"get_concepts_for_paper(arxiv_id=\"1804.09057\")"}],"by_repo":[{"repo":"ZhenYangIACAS/unsupervised-NMT","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0}],"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":"4fcc864e0e50c25ad4a3acec81f5edcbda325a1b84f47dbdcf31365f85639634","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}