{"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/consistency-by-agreement-in-zero-shot-neural","title":"Consistency by Agreement in Zero-shot Neural Machine Translation","arxiv_id":"1904.02338","date":"2019-04-04","proceeding":"NAACL 2019 6","authors":["Maruan Al-Shedivat","Ankur P. Parikh"],"abstract":"Generalization and reliability of multilingual translation often highly\ndepend on the amount of available parallel data for each language pair of\ninterest. In this paper, we focus on zero-shot generalization---a challenging\nsetup that tests models on translation directions they have not been optimized\nfor at training time. To solve the problem, we (i) reformulate multilingual\ntranslation as probabilistic inference, (ii) define the notion of zero-shot\nconsistency and show why standard training often results in models unsuitable\nfor zero-shot tasks, and (iii) introduce a consistent agreement-based training\nmethod that encourages the model to produce equivalent translations of parallel\nsentences in auxiliary languages. We test our multilingual NMT models on\nmultiple public zero-shot translation benchmarks (IWSLT17, UN corpus, Europarl)\nand show that agreement-based learning often results in 2-3 BLEU zero-shot\nimprovement over strong baselines without any loss in performance on supervised\ntranslation directions.","url_abs":"http://arxiv.org/abs/1904.02338v2","url_pdf":"http://arxiv.org/pdf/1904.02338v2.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":"consistency-by-agreement-in-zero-shot-neural","repo_url":"https://github.com/google-research/language/tree/master/language/labs/consistent_zero_shot_nmt","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"tf","reach":null},{"paper_slug":"consistency-by-agreement-in-zero-shot-neural","repo_url":"https://github.com/google-research/language","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"tf","reach":null}],"tasks":[{"task_slug":"machine-translation","task_name":"Machine Translation"},{"task_slug":"nmt","task_name":"NMT"},{"task_slug":"translation","task_name":"Translation"},{"task_slug":"zero-shot-machine-translation","task_name":"Zero-Shot Machine Translation"},{"task_slug":"zero-shot-generalization","task_name":"Zero-shot Generalization"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1904.02338","atlas_url":"https://app.syntology.ai/?focus=1904.02338","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":"1904.02338"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1904.02338\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1904.02338"},"call":"get_concepts_for_paper(arxiv_id=\"1904.02338\")"}],"by_repo":[{"repo":"google-research/language","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2106.16163"],"harvested_for_calls":[{"arxiv_id":"2106.16163","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2106.16163"},"call":"get_harvested_code_for_paper(arxiv_id=\"2106.16163\")"}]}],"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":"0a91be35917b90a47b79d9b017fe1d3f9e07bc4c5d53ae8bee438a7baa2d0f74","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}