{"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/exploring-recombination-for-efficient","title":"Exploring Recombination for Efficient Decoding of Neural Machine Translation","arxiv_id":"1808.08482","date":"2018-08-25","proceeding":"EMNLP 2018 10","authors":["Zhisong Zhang","Rui Wang","Masao Utiyama","Eiichiro Sumita","Hai Zhao"],"abstract":"In Neural Machine Translation (NMT), the decoder can capture the features of\nthe entire prediction history with neural connections and representations. This\nmeans that partial hypotheses with different prefixes will be regarded\ndifferently no matter how similar they are. However, this might be inefficient\nsince some partial hypotheses can contain only local differences that will not\ninfluence future predictions. In this work, we introduce recombination in NMT\ndecoding based on the concept of the \"equivalence\" of partial hypotheses.\nHeuristically, we use a simple $n$-gram suffix based equivalence function and\nadapt it into beam search decoding. Through experiments on large-scale\nChinese-to-English and English-to-Germen translation tasks, we show that the\nproposed method can obtain similar translation quality with a smaller beam\nsize, making NMT decoding more efficient.","url_abs":"http://arxiv.org/abs/1808.08482v2","url_pdf":"http://arxiv.org/pdf/1808.08482v2.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":"exploring-recombination-for-efficient","repo_url":"https://github.com/zzsfornlp/znmt-merge","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":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}