{"about":{"site":"https://codewithpapers.app","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.","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"},"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":null,"atlas_url":"https://app.syntology.ai/?focus=1904.02338","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}