{"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/exploiting-cross-sentence-context-for-neural","title":"Exploiting Cross-Sentence Context for Neural Machine Translation","arxiv_id":"1704.04347","date":"2017-04-14","proceeding":"EMNLP 2017 9","authors":["Long-Yue Wang","Zhaopeng Tu","Andy Way","Qun Liu"],"abstract":"In translation, considering the document as a whole can help to resolve\nambiguities and inconsistencies. In this paper, we propose a cross-sentence\ncontext-aware approach and investigate the influence of historical contextual\ninformation on the performance of neural machine translation (NMT). First, this\nhistory is summarized in a hierarchical way. We then integrate the historical\nrepresentation into NMT in two strategies: 1) a warm-start of encoder and\ndecoder states, and 2) an auxiliary context source for updating decoder states.\nExperimental results on a large Chinese-English translation task show that our\napproach significantly improves upon a strong attention-based NMT system by up\nto +2.1 BLEU points.","url_abs":"http://arxiv.org/abs/1704.04347v3","url_pdf":"http://arxiv.org/pdf/1704.04347v3.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":"exploiting-cross-sentence-context-for-neural","repo_url":"https://github.com/tuzhaopeng/LC-NMT","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"unanswered"}}],"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":"https://app.syntology.ai/?focus=1704.04347","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}