{"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/improved-neural-machine-translation-with-a","title":"Improved Neural Machine Translation with a Syntax-Aware Encoder and Decoder","arxiv_id":"1707.05436","date":"2017-07-18","proceeding":"ACL 2017 7","authors":["Huadong Chen","Shu-Jian Huang","David Chiang","Jia-Jun Chen"],"abstract":"Most neural machine translation (NMT) models are based on the sequential\nencoder-decoder framework, which makes no use of syntactic information. In this\npaper, we improve this model by explicitly incorporating source-side syntactic\ntrees. More specifically, we propose (1) a bidirectional tree encoder which\nlearns both sequential and tree structured representations; (2) a tree-coverage\nmodel that lets the attention depend on the source-side syntax. Experiments on\nChinese-English translation demonstrate that our proposed models outperform the\nsequential attentional model as well as a stronger baseline with a bottom-up\ntree encoder and word coverage.","url_abs":"http://arxiv.org/abs/1707.05436v1","url_pdf":"http://arxiv.org/pdf/1707.05436v1.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":"improved-neural-machine-translation-with-a","repo_url":"https://github.com/howardchenhd/Syntax-awared-NMT","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"decoder","task_name":"Decoder"},{"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":{"syntology_url":"https://syntology.ai/paper/1707.05436","atlas_url":"https://app.syntology.ai/?focus=1707.05436","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}