{"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-parse-and-translate-improves","title":"Learning to Parse and Translate Improves Neural Machine Translation","arxiv_id":"1702.03525","date":"2017-02-12","proceeding":"ACL 2017 7","authors":["Akiko Eriguchi","Yoshimasa Tsuruoka","Kyunghyun Cho"],"abstract":"There has been relatively little attention to incorporating linguistic prior\nto neural machine translation. Much of the previous work was further\nconstrained to considering linguistic prior on the source side. In this paper,\nwe propose a hybrid model, called NMT+RNNG, that learns to parse and translate\nby combining the recurrent neural network grammar into the attention-based\nneural machine translation. Our approach encourages the neural machine\ntranslation model to incorporate linguistic prior during training, and lets it\ntranslate on its own afterward. Extensive experiments with four language pairs\nshow the effectiveness of the proposed NMT+RNNG.","url_abs":"http://arxiv.org/abs/1702.03525v2","url_pdf":"http://arxiv.org/pdf/1702.03525v2.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-parse-and-translate-improves","repo_url":"https://github.com/tempra28/nmtrnng","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}}],"tasks":[{"task_slug":"machine-translation","task_name":"Machine Translation"},{"task_slug":"nmt","task_name":"NMT"},{"task_slug":"translation","task_name":"Translation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1702.03525","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}