{"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/chunk-based-bi-scale-decoder-for-neural","title":"Chunk-Based Bi-Scale Decoder for Neural Machine Translation","arxiv_id":"1705.01452","date":"2017-05-03","proceeding":"ACL 2017 7","authors":["Hao Zhou","Zhaopeng Tu","Shu-Jian Huang","Xiaohua Liu","Hang Li","Jia-Jun Chen"],"abstract":"In typical neural machine translation~(NMT), the decoder generates a sentence\nword by word, packing all linguistic granularities in the same time-scale of\nRNN. In this paper, we propose a new type of decoder for NMT, which splits the\ndecode state into two parts and updates them in two different time-scales.\nSpecifically, we first predict a chunk time-scale state for phrasal modeling,\non top of which multiple word time-scale states are generated. In this way, the\ntarget sentence is translated hierarchically from chunks to words, with\ninformation in different granularities being leveraged. Experiments show that\nour proposed model significantly improves the translation performance over the\nstate-of-the-art NMT model.","url_abs":"http://arxiv.org/abs/1705.01452v1","url_pdf":"http://arxiv.org/pdf/1705.01452v1.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":"chunk-based-bi-scale-decoder-for-neural","repo_url":"https://github.com/zhouh/chunk-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":"sentence","task_name":"Sentence"},{"task_slug":"translation","task_name":"Translation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}