{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/beam-search-strategies-for-neural-machine","title":"Beam Search Strategies for Neural Machine Translation","arxiv_id":"1702.01806","date":"2017-02-06","proceeding":"WS 2017 8","authors":["Markus Freitag","Yaser Al-Onaizan"],"abstract":"The basic concept in Neural Machine Translation (NMT) is to train a large\nNeural Network that maximizes the translation performance on a given parallel\ncorpus. NMT is then using a simple left-to-right beam-search decoder to\ngenerate new translations that approximately maximize the trained conditional\nprobability. The current beam search strategy generates the target sentence\nword by word from left-to- right while keeping a fixed amount of active\ncandidates at each time step. First, this simple search is less adaptive as it\nalso expands candidates whose scores are much worse than the current best.\nSecondly, it does not expand hypotheses if they are not within the best scoring\ncandidates, even if their scores are close to the best one. The latter one can\nbe avoided by increasing the beam size until no performance improvement can be\nobserved. While you can reach better performance, this has the draw- back of a\nslower decoding speed. In this paper, we concentrate on speeding up the decoder\nby applying a more flexible beam search strategy whose candidate size may vary\nat each time step depending on the candidate scores. We speed up the original\ndecoder by up to 43% for the two language pairs German-English and\nChinese-English without losing any translation quality.","url_abs":"http://arxiv.org/abs/1702.01806v2","url_pdf":"http://arxiv.org/pdf/1702.01806v2.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":"beam-search-strategies-for-neural-machine","repo_url":"https://github.com/CongBao/ChatBot","is_official":0,"mentioned_in_paper":0,"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":[{"method_slug":"speed","method_name":"SPEED"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1702.01806","atlas_url":"https://app.syntology.ai/?focus=1702.01806","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"1702.01806"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1702.01806\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1702.01806"},"call":"get_concepts_for_paper(arxiv_id=\"1702.01806\")"}],"by_repo":[{"repo":"CongBao/ChatBot","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0}],"by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"49bdd0fa3ee87be7cf76c8c17b1463593f0513bce320ec2815d78246e3153dff","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}