{"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/recurrent-neural-network-regularization","title":"Recurrent Neural Network Regularization","arxiv_id":"1409.2329","date":"2014-09-08","proceeding":null,"authors":["Wojciech Zaremba","Ilya Sutskever","Oriol Vinyals"],"abstract":"We present a simple regularization technique for Recurrent Neural Networks\n(RNNs) with Long Short-Term Memory (LSTM) units. Dropout, the most successful\ntechnique for regularizing neural networks, does not work well with RNNs and\nLSTMs. In this paper, we show how to correctly apply dropout to LSTMs, and show\nthat it substantially reduces overfitting on a variety of tasks. These tasks\ninclude language modeling, speech recognition, image caption generation, and\nmachine translation.","url_abs":"http://arxiv.org/abs/1409.2329v5","url_pdf":"http://arxiv.org/pdf/1409.2329v5.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":"recurrent-neural-network-regularization","repo_url":"https://github.com/wojzaremba/lstm","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"recurrent-neural-network-regularization","repo_url":"https://github.com/FredericGodin/QuasiRNN-DReLU","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"recurrent-neural-network-regularization","repo_url":"https://github.com/Goodideax/lstm-negtive","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"recurrent-neural-network-regularization","repo_url":"https://github.com/Goodideax/rnn_neg_efficient","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"recurrent-neural-network-regularization","repo_url":"https://github.com/ahmetumutdurmus/zaremba","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"recurrent-neural-network-regularization","repo_url":"https://github.com/dhecloud/simple_language_modelling","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"recurrent-neural-network-regularization","repo_url":"https://github.com/floydhub/word-language-model","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"recurrent-neural-network-regularization","repo_url":"https://github.com/hikaruya8/lstm_model_py","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"recurrent-neural-network-regularization","repo_url":"https://github.com/hjc18/language_modeling_lstm","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"recurrent-neural-network-regularization","repo_url":"https://github.com/isi-nlp/Zoph_RNN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"recurrent-neural-network-regularization","repo_url":"https://github.com/martin-gorner/tensorflow-rnn-shakespeare","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"recurrent-neural-network-regularization","repo_url":"https://github.com/nbansal90/bAbi_QA","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"recurrent-neural-network-regularization","repo_url":"https://github.com/rgarzonj/LSTMs","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"recurrent-neural-network-regularization","repo_url":"https://github.com/sebastianGehrmann/tensorflow-statereader","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"recurrent-neural-network-regularization","repo_url":"https://github.com/shivam13juna/Sequence_Prediction_LSTM_CHAR","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"recurrent-neural-network-regularization","repo_url":"https://github.com/simon-benigeri/lstm-language-model","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"recurrent-neural-network-regularization","repo_url":"https://github.com/tmatha/lstm","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"recurrent-neural-network-regularization","repo_url":"https://github.com/tomsercu/lstm","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"recurrent-neural-network-regularization","repo_url":"https://github.com/MindSpore-scientific/code-14/tree/main/ReSeg","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"recurrent-neural-network-regularization","repo_url":"https://github.com/MindSpore-scientific/code-5/tree/main/ReSeg","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"recurrent-neural-network-regularization","repo_url":"https://github.com/jincan333/lot","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"caption-generation","task_name":"Caption Generation"},{"task_slug":"image-captioning","task_name":"Image Captioning"},{"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":"speech-recognition","task_name":"Speech Recognition"},{"task_slug":"translation","task_name":"Translation"}],"methods":[{"method_slug":"dropout","method_name":"Dropout"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/language-modelling-on-penn-treebank-word","task":"Language Modelling","dataset":"Penn Treebank (Word Level)","model":"Zaremba et al. (2014) - LSTM (large)","rank_in_archive_order":36,"of":43,"metrics":{"Test perplexity":"78.4","Validation perplexity":"82.2"},"uses_additional_data":false},{"leaderboard":"/sota/language-modelling-on-penn-treebank-word","task":"Language Modelling","dataset":"Penn Treebank (Word Level)","model":"Zaremba et al. (2014) - LSTM (medium)","rank_in_archive_order":39,"of":43,"metrics":{"Test perplexity":"82.7","Validation perplexity":"86.2"},"uses_additional_data":false},{"leaderboard":"/sota/machine-translation-on-wmt2014-english-french","task":"Machine Translation","dataset":"WMT2014 English-French","model":"Regularized LSTM","rank_in_archive_order":51,"of":57,"metrics":{"BLEU score":"29.03"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1409.2329","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1409.2329"}},"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/MindSpore-scientific/code-14/tree/main/ReSeg","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/simon-benigeri/lstm-language-model","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/rgarzonj/LSTMs","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Goodideax/lstm-negtive","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/martin-gorner/tensorflow-rnn-shakespeare","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/wojzaremba/lstm","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/shivam13juna/Sequence_Prediction_LSTM_CHAR","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/hjc18/language_modeling_lstm","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/nbansal90/bAbi_QA","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/MindSpore-scientific/code-5/tree/main/ReSeg","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Goodideax/rnn_neg_efficient","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/jincan333/lot","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/ahmetumutdurmus/zaremba","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/hikaruya8/lstm_model_py","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/floydhub/word-language-model","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/sebastianGehrmann/tensorflow-statereader","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/FredericGodin/QuasiRNN-DReLU","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/isi-nlp/Zoph_RNN","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/dhecloud/simple_language_modelling","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/tmatha/lstm","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/tomsercu/lstm","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran_draft_wrong":2,"unverified":4},"by_repo_kind":{"listed":{"samples":6,"ran":2,"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":6,"samples":[{"code_sha256_prefix":"07d70b54781a432d","entry":"minibatch","repo":"Goodideax/lstm-negtive","repo_kind":"listed","path":"ensemble.py","file_url":"https://github.com/Goodideax/lstm-negtive/blob/HEAD/ensemble.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"07d70b54781a432d"}},{"code_sha256_prefix":"dd2e42e616936d7a","entry":"nll_loss","repo":"Goodideax/lstm-negtive","repo_kind":"listed","path":"ensemble.py","file_url":"https://github.com/Goodideax/lstm-negtive/blob/HEAD/ensemble.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"dd2e42e616936d7a"}},{"code_sha256_prefix":"773bac171b472d67","entry":"create_ptb_loader","repo":"dhecloud/simple_language_modelling","repo_kind":"listed","path":"train_lm.py","file_url":"https://github.com/dhecloud/simple_language_modelling/blob/HEAD/train_lm.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"773bac171b472d67"}},{"code_sha256_prefix":"463f26abb478a418","entry":"eval","repo":"dhecloud/simple_language_modelling","repo_kind":"listed","path":"train_lm.py","file_url":"https://github.com/dhecloud/simple_language_modelling/blob/HEAD/train_lm.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"463f26abb478a418"}},{"code_sha256_prefix":"d8b96d7fec1ed277","entry":"perplexity","repo":"Goodideax/lstm-negtive","repo_kind":"listed","path":"ensemble.py","file_url":"https://github.com/Goodideax/lstm-negtive/blob/HEAD/ensemble.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"d8b96d7fec1ed277"}},{"code_sha256_prefix":"eae89d8a906f77fb","entry":"train","repo":"dhecloud/simple_language_modelling","repo_kind":"listed","path":"train_lm.py","file_url":"https://github.com/dhecloud/simple_language_modelling/blob/HEAD/train_lm.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"eae89d8a906f77fb"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}