{"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/learning-to-translate-in-real-time-with","title":"Learning to Translate in Real-time with Neural Machine Translation","arxiv_id":"1610.00388","date":"2016-10-03","proceeding":"EACL 2017 4","authors":["Jiatao Gu","Graham Neubig","Kyunghyun Cho","Victor O. K. Li"],"abstract":"Translating in real-time, a.k.a. simultaneous translation, outputs\ntranslation words before the input sentence ends, which is a challenging\nproblem for conventional machine translation methods. We propose a neural\nmachine translation (NMT) framework for simultaneous translation in which an\nagent learns to make decisions on when to translate from the interaction with a\npre-trained NMT environment. To trade off quality and delay, we extensively\nexplore various targets for delay and design a method for beam-search\napplicable in the simultaneous MT setting. Experiments against state-of-the-art\nbaselines on two language pairs demonstrate the efficacy of the proposed\nframework both quantitatively and qualitatively.","url_abs":"http://arxiv.org/abs/1610.00388v3","url_pdf":"http://arxiv.org/pdf/1610.00388v3.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":"learning-to-translate-in-real-time-with","repo_url":"https://github.com/nyu-dl/dl4mt-simul-trans","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","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"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1610.00388","atlas_url":"https://app.syntology.ai/?focus=1610.00388","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}