{"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/tree-to-sequence-attentional-neural-machine","title":"Tree-to-Sequence Attentional Neural Machine Translation","arxiv_id":"1603.06075","date":"2016-03-19","proceeding":"ACL 2016 8","authors":["Akiko Eriguchi","Kazuma Hashimoto","Yoshimasa Tsuruoka"],"abstract":"Most of the existing Neural Machine Translation (NMT) models focus on the\nconversion of sequential data and do not directly use syntactic information. We\npropose a novel end-to-end syntactic NMT model, extending a\nsequence-to-sequence model with the source-side phrase structure. Our model has\nan attention mechanism that enables the decoder to generate a translated word\nwhile softly aligning it with phrases as well as words of the source sentence.\nExperimental results on the WAT'15 English-to-Japanese dataset demonstrate that\nour proposed model considerably outperforms sequence-to-sequence attentional\nNMT models and compares favorably with the state-of-the-art tree-to-string SMT\nsystem.","url_abs":"http://arxiv.org/abs/1603.06075v3","url_pdf":"http://arxiv.org/pdf/1603.06075v3.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":"tree-to-sequence-attentional-neural-machine","repo_url":"https://github.com/tempra28/tree2seq","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}}],"tasks":[{"task_slug":"decoder","task_name":"Decoder"},{"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":null,"atlas_url":"https://app.syntology.ai/?focus=1603.06075","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}