{"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/single-queue-decoding-for-neural-machine","title":"Single-Queue Decoding for Neural Machine Translation","arxiv_id":"1707.01830","date":"2017-07-06","proceeding":null,"authors":["Raphael Shu","Hideki Nakayama"],"abstract":"Neural machine translation models rely on the beam search algorithm for\ndecoding. In practice, we found that the quality of hypotheses in the search\nspace is negatively affected owing to the fixed beam size. To mitigate this\nproblem, we store all hypotheses in a single priority queue and use a universal\nscore function for hypothesis selection. The proposed algorithm is more\nflexible as the discarded hypotheses can be revisited in a later step. We\nfurther design a penalty function to punish the hypotheses that tend to produce\na final translation that is much longer or shorter than expected. Despite its\nsimplicity, we show that the proposed decoding algorithm is able to select\nhypotheses with better qualities and improve the translation performance.","url_abs":"http://arxiv.org/abs/1707.01830v2","url_pdf":"http://arxiv.org/pdf/1707.01830v2.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":"single-queue-decoding-for-neural-machine","repo_url":"https://github.com/zomux/nmtdec","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"machine-translation","task_name":"Machine Translation"},{"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}