{"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/scheduled-sampling-for-sequence-prediction","title":"Scheduled Sampling for Sequence Prediction with Recurrent Neural Networks","arxiv_id":"1506.03099","date":"2015-06-09","proceeding":"NeurIPS 2015 12","authors":["Samy Bengio","Oriol Vinyals","Navdeep Jaitly","Noam Shazeer"],"abstract":"Recurrent Neural Networks can be trained to produce sequences of tokens given\nsome input, as exemplified by recent results in machine translation and image\ncaptioning. The current approach to training them consists of maximizing the\nlikelihood of each token in the sequence given the current (recurrent) state\nand the previous token. At inference, the unknown previous token is then\nreplaced by a token generated by the model itself. This discrepancy between\ntraining and inference can yield errors that can accumulate quickly along the\ngenerated sequence. We propose a curriculum learning strategy to gently change\nthe training process from a fully guided scheme using the true previous token,\ntowards a less guided scheme which mostly uses the generated token instead.\nExperiments on several sequence prediction tasks show that this approach yields\nsignificant improvements. Moreover, it was used successfully in our winning\nentry to the MSCOCO image captioning challenge, 2015.","url_abs":"http://arxiv.org/abs/1506.03099v3","url_pdf":"http://arxiv.org/pdf/1506.03099v3.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":"scheduled-sampling-for-sequence-prediction","repo_url":"https://github.com/BugOMan/summary_generator","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"scheduled-sampling-for-sequence-prediction","repo_url":"https://github.com/Chung-I/Variational-Recurrent-Autoencoder-Tensorflow","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"scheduled-sampling-for-sequence-prediction","repo_url":"https://github.com/IPINGCHOU/NTU_MachineLearning","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"scheduled-sampling-for-sequence-prediction","repo_url":"https://github.com/ThisuriLekamge/Stock-Price-Prediction-on-Bitcoin-trading-data-using-LSTM-with-PyTorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"scheduled-sampling-for-sequence-prediction","repo_url":"https://github.com/kaikai-sk/char-rnn-chinese","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"torch","reach":{"status":"ok"}},{"paper_slug":"scheduled-sampling-for-sequence-prediction","repo_url":"https://github.com/oneway3124/disaggregation-vrnn","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"scheduled-sampling-for-sequence-prediction","repo_url":"https://github.com/oplatek/e2end","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"scheduled-sampling-for-sequence-prediction","repo_url":"https://github.com/zhangzibin/char-rnn-chinese","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"torch","reach":{"status":"ok"}},{"paper_slug":"scheduled-sampling-for-sequence-prediction","repo_url":"https://github.com/theamrzaki/text_summurization_abstractive_methods","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"tf","reach":{"status":"ok"}}],"tasks":[{"task_slug":"constituency-parsing","task_name":"Constituency Parsing"},{"task_slug":"image-captioning","task_name":"Image Captioning"},{"task_slug":"prediction","task_name":"Prediction"},{"task_slug":"speech-recognition","task_name":"Speech Recognition"},{"task_slug":"translation","task_name":"Translation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1506.03099","atlas_url":"https://app.syntology.ai/?focus=1506.03099","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1506.03099"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/Chung-I/Variational-Recurrent-Autoencoder-Tensorflow","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/IPINGCHOU/NTU_MachineLearning","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/oneway3124/disaggregation-vrnn","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/zhangzibin/char-rnn-chinese","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/BugOMan/summary_generator","reach":{"status":"ok","spdx":"NOASSERTION"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/ThisuriLekamge/Stock-Price-Prediction-on-Bitcoin-trading-data-using-LSTM-with-PyTorch","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/theamrzaki/text_summurization_abstractive_methods","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/kaikai-sk/char-rnn-chinese","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/oplatek/e2end","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"unverified":8},"by_repo_kind":{"listed":{"samples":8,"ran":0,"repositories":1}},"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":"c0f1bfe2a7139f20","entry":"attention_decoder","repo":"oplatek/e2end","repo_kind":"listed","path":"e2end/model/decoder.py","file_url":"https://github.com/oplatek/e2end/blob/HEAD/e2end/model/decoder.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"c0f1bfe2a7139f20"}},{"code_sha256_prefix":"f4350f932bd9743b","entry":"get_bleus","repo":"oplatek/e2end","repo_kind":"listed","path":"e2end/model/evaluation.py","file_url":"https://github.com/oplatek/e2end/blob/HEAD/e2end/model/evaluation.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"f4350f932bd9743b"}},{"code_sha256_prefix":"8694c9cd02e9f95c","entry":"shuffle","repo":"oplatek/e2end","repo_kind":"listed","path":"e2end/utils.py","file_url":"https://github.com/oplatek/e2end/blob/HEAD/e2end/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"8694c9cd02e9f95c"}},{"code_sha256_prefix":"7386793e4883e20c","entry":"sigmoid","repo":"oplatek/e2end","repo_kind":"listed","path":"e2end/utils.py","file_url":"https://github.com/oplatek/e2end/blob/HEAD/e2end/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"7386793e4883e20c"}},{"code_sha256_prefix":"e60cce6899e60e6a","entry":"split","repo":"oplatek/e2end","repo_kind":"listed","path":"e2end/utils.py","file_url":"https://github.com/oplatek/e2end/blob/HEAD/e2end/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"e60cce6899e60e6a"}},{"code_sha256_prefix":"460d6c8b80434cd2","entry":"tf_lengths2mask2d","repo":"oplatek/e2end","repo_kind":"listed","path":"e2end/model/evaluation.py","file_url":"https://github.com/oplatek/e2end/blob/HEAD/e2end/model/evaluation.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"460d6c8b80434cd2"}},{"code_sha256_prefix":"297bf6be5afe88c9","entry":"tf_trg_word2vocab_id","repo":"oplatek/e2end","repo_kind":"listed","path":"e2end/model/evaluation.py","file_url":"https://github.com/oplatek/e2end/blob/HEAD/e2end/model/evaluation.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"297bf6be5afe88c9"}},{"code_sha256_prefix":"7c61a46975e737a8","entry":"word_db_embed_attention_decoder","repo":"oplatek/e2end","repo_kind":"listed","path":"e2end/model/decoder.py","file_url":"https://github.com/oplatek/e2end/blob/HEAD/e2end/model/decoder.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"7c61a46975e737a8"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}