{"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/sequence-to-sequence-learning-as-beam-search","title":"Sequence-to-Sequence Learning as Beam-Search Optimization","arxiv_id":"1606.02960","date":"2016-06-09","proceeding":"EMNLP 2016 11","authors":["Sam Wiseman","Alexander M. Rush"],"abstract":"Sequence-to-Sequence (seq2seq) modeling has rapidly become an important\ngeneral-purpose NLP tool that has proven effective for many text-generation and\nsequence-labeling tasks. Seq2seq builds on deep neural language modeling and\ninherits its remarkable accuracy in estimating local, next-word distributions.\nIn this work, we introduce a model and beam-search training scheme, based on\nthe work of Daume III and Marcu (2005), that extends seq2seq to learn global\nsequence scores. This structured approach avoids classical biases associated\nwith local training and unifies the training loss with the test-time usage,\nwhile preserving the proven model architecture of seq2seq and its efficient\ntraining approach. We show that our system outperforms a highly-optimized\nattention-based seq2seq system and other baselines on three different sequence\nto sequence tasks: word ordering, parsing, and machine translation.","url_abs":"http://arxiv.org/abs/1606.02960v2","url_pdf":"http://arxiv.org/pdf/1606.02960v2.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":"sequence-to-sequence-learning-as-beam-search","repo_url":"https://github.com/harvardnlp/BSO","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"sequence-to-sequence-learning-as-beam-search","repo_url":"https://github.com/facebookresearch/fairseq","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"sequence-to-sequence-learning-as-beam-search","repo_url":"https://github.com/joeynmt/joeynmt","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"sequence-to-sequence-learning-as-beam-search","repo_url":"https://github.com/juliakreutzer/joeynmt","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"sequence-to-sequence-learning-as-beam-search","repo_url":"https://github.com/sgrvinod/a-PyTorch-Tutorial-to-Image-Captioning","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"sequence-to-sequence-learning-as-beam-search","repo_url":"https://github.com/AndreiMoraru123/ContextCollector","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"machine-translation","task_name":"Machine Translation"},{"task_slug":"text-generation","task_name":"Text Generation"},{"task_slug":"translation","task_name":"Translation"}],"methods":[{"method_slug":"lstm","method_name":"LSTM"},{"method_slug":"seq2seq","method_name":"Seq2Seq"},{"method_slug":"sigmoid-activation","method_name":"Sigmoid Activation"},{"method_slug":"tanh-activation","method_name":"Tanh Activation"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/machine-translation-on-iwslt2015-german","task":"Machine Translation","dataset":"IWSLT2015 German-English","model":"Word-level CNN w/attn, input feeding","rank_in_archive_order":13,"of":15,"metrics":{"BLEU score":"24.0"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1606.02960","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1606.02960"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/facebookresearch/fairseq","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/sgrvinod/a-PyTorch-Tutorial-to-Image-Captioning","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/juliakreutzer/joeynmt","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/joeynmt/joeynmt","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/AndreiMoraru123/ContextCollector","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/harvardnlp/BSO","reach":{"status":"ok"}}],"summary":{"ran":1,"unverified":7},"by_repo_kind":{"listed":{"samples":8,"ran":1,"repositories":2}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"53daad1d7b99fbdf","entry":"accuracy","repo":"sgrvinod/a-PyTorch-Tutorial-to-Image-Captioning","repo_kind":"listed","path":"utils.py","file_url":"https://github.com/sgrvinod/a-PyTorch-Tutorial-to-Image-Captioning/blob/HEAD/utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"53daad1d7b99fbdf"}},{"code_sha256_prefix":"0b8377535f19b59a","entry":"boxes_iou","repo":"AndreiMoraru123/ContextCollector","repo_kind":"listed","path":"YOLO/utils.py","file_url":"https://github.com/AndreiMoraru123/ContextCollector/blob/HEAD/YOLO/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"0b8377535f19b59a"}},{"code_sha256_prefix":"5758971f4ecbc2dd","entry":"detect_objects","repo":"AndreiMoraru123/ContextCollector","repo_kind":"listed","path":"YOLO/utils.py","file_url":"https://github.com/AndreiMoraru123/ContextCollector/blob/HEAD/YOLO/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"5758971f4ecbc2dd"}},{"code_sha256_prefix":"4cc9097b30b644e0","entry":"load_embeddings","repo":"sgrvinod/a-PyTorch-Tutorial-to-Image-Captioning","repo_kind":"listed","path":"utils.py","file_url":"https://github.com/sgrvinod/a-PyTorch-Tutorial-to-Image-Captioning/blob/HEAD/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"4cc9097b30b644e0"}},{"code_sha256_prefix":"87488d598797633f","entry":"nms","repo":"AndreiMoraru123/ContextCollector","repo_kind":"listed","path":"YOLO/utils.py","file_url":"https://github.com/AndreiMoraru123/ContextCollector/blob/HEAD/YOLO/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"87488d598797633f"}},{"code_sha256_prefix":"8d85fd25730c83cd","entry":"prune_model_l1_structured","repo":"AndreiMoraru123/ContextCollector","repo_kind":"listed","path":"pipeline.py","file_url":"https://github.com/AndreiMoraru123/ContextCollector/blob/HEAD/pipeline.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"8d85fd25730c83cd"}},{"code_sha256_prefix":"05d051969149aebe","entry":"prune_model_l1_unstructured","repo":"AndreiMoraru123/ContextCollector","repo_kind":"listed","path":"pipeline.py","file_url":"https://github.com/AndreiMoraru123/ContextCollector/blob/HEAD/pipeline.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"05d051969149aebe"}},{"code_sha256_prefix":"49254e079390a7e2","entry":"prune_model_l2_structured","repo":"AndreiMoraru123/ContextCollector","repo_kind":"listed","path":"pipeline.py","file_url":"https://github.com/AndreiMoraru123/ContextCollector/blob/HEAD/pipeline.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"49254e079390a7e2"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}