{"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/an-analysis-of-neural-language-modeling-at","title":"An Analysis of Neural Language Modeling at Multiple Scales","arxiv_id":"1803.08240","date":"2018-03-22","proceeding":null,"authors":["Stephen Merity","Nitish Shirish Keskar","Richard Socher"],"abstract":"Many of the leading approaches in language modeling introduce novel, complex\nand specialized architectures. We take existing state-of-the-art word level\nlanguage models based on LSTMs and QRNNs and extend them to both larger\nvocabularies as well as character-level granularity. When properly tuned, LSTMs\nand QRNNs achieve state-of-the-art results on character-level (Penn Treebank,\nenwik8) and word-level (WikiText-103) datasets, respectively. Results are\nobtained in only 12 hours (WikiText-103) to 2 days (enwik8) using a single\nmodern GPU.","url_abs":"http://arxiv.org/abs/1803.08240v1","url_pdf":"http://arxiv.org/pdf/1803.08240v1.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":"an-analysis-of-neural-language-modeling-at","repo_url":"https://github.com/salesforce/awd-lstm-lm","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"BSD-3-Clause"}},{"paper_slug":"an-analysis-of-neural-language-modeling-at","repo_url":"https://github.com/AtheMathmo/lookahead-lstm","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"BSD-3-Clause"}},{"paper_slug":"an-analysis-of-neural-language-modeling-at","repo_url":"https://github.com/Han-JD/GRU-D","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"an-analysis-of-neural-language-modeling-at","repo_url":"https://github.com/SachinIchake/KALM","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"BSD-3-Clause"}},{"paper_slug":"an-analysis-of-neural-language-modeling-at","repo_url":"https://github.com/ari-holtzman/genlm","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"BSD-3-Clause"}},{"paper_slug":"an-analysis-of-neural-language-modeling-at","repo_url":"https://github.com/arvieFrydenlund/awd-lstm-lm","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"BSD-3-Clause"}},{"paper_slug":"an-analysis-of-neural-language-modeling-at","repo_url":"https://github.com/jb33k/awd-lstm-lm-ThinkNet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"BSD-3-Clause"}},{"paper_slug":"an-analysis-of-neural-language-modeling-at","repo_url":"https://github.com/llppff/ptb-lstmorqrnn-pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"BSD-3-Clause"}},{"paper_slug":"an-analysis-of-neural-language-modeling-at","repo_url":"https://github.com/mnhng/hier-char-emb","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"BSD-3-Clause"}},{"paper_slug":"an-analysis-of-neural-language-modeling-at","repo_url":"https://github.com/philippwirth/awd-lstm-test","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"BSD-3-Clause"}},{"paper_slug":"an-analysis-of-neural-language-modeling-at","repo_url":"https://github.com/philippwirth/treelangrnn","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"BSD-3-Clause"}},{"paper_slug":"an-analysis-of-neural-language-modeling-at","repo_url":"https://github.com/soyoung97/awd-lstm-gru","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"BSD-3-Clause"}}],"tasks":[{"task_slug":null,"task_name":"GPU"},{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/language-modelling-on-hutter-prize","task":"Language Modelling","dataset":"Hutter Prize","model":"3-layer AWD-LSTM","rank_in_archive_order":13,"of":18,"metrics":{"Bit per Character (BPC)":"1.232","Number of params":"47M"},"uses_additional_data":false},{"leaderboard":"/sota/language-modelling-on-penn-treebank-character","task":"Language Modelling","dataset":"Penn Treebank (Character Level)","model":"3-layer AWD-LSTM","rank_in_archive_order":7,"of":20,"metrics":{"Bit per Character (BPC)":"1.175","Number of params":"13.8M"},"uses_additional_data":false},{"leaderboard":"/sota/language-modelling-on-penn-treebank-character","task":"Language Modelling","dataset":"Penn Treebank (Character Level)","model":"6-layer QRNN","rank_in_archive_order":9,"of":20,"metrics":{"Bit per Character (BPC)":"1.187","Number of params":"13.8M"},"uses_additional_data":false},{"leaderboard":"/sota/language-modelling-on-wikitext-103","task":"Language Modelling","dataset":"WikiText-103","model":"4 layer QRNN","rank_in_archive_order":75,"of":89,"metrics":{"Number of params":"151M","Test perplexity":"33.0","Validation perplexity":"32.0"},"uses_additional_data":false},{"leaderboard":"/sota/language-modelling-on-enwiki8","task":"Language Modelling","dataset":"enwik8","model":"AWD-LSTM (3 layers)","rank_in_archive_order":33,"of":42,"metrics":{"Bit per Character (BPC)":"1.232","Number of params":"47M"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=1803.08240","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1803.08240"}},"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/llppff/ptb-lstmorqrnn-pytorch","reach":{"status":"ok","spdx":"BSD-3-Clause"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/mnhng/hier-char-emb","reach":{"status":"ok","spdx":"BSD-3-Clause"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Han-JD/GRU-D","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/AtheMathmo/lookahead-lstm","reach":{"status":"ok","spdx":"BSD-3-Clause"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/jb33k/awd-lstm-lm-ThinkNet","reach":{"status":"ok","spdx":"BSD-3-Clause"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/SachinIchake/KALM","reach":{"status":"ok","spdx":"BSD-3-Clause"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/philippwirth/treelangrnn","reach":{"status":"ok","spdx":"BSD-3-Clause"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/ari-holtzman/genlm","reach":{"status":"ok","spdx":"BSD-3-Clause"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/arvieFrydenlund/awd-lstm-lm","reach":{"status":"ok","spdx":"BSD-3-Clause"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/philippwirth/awd-lstm-test","reach":{"status":"ok","spdx":"BSD-3-Clause"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/soyoung97/awd-lstm-gru","reach":{"status":"ok","spdx":"BSD-3-Clause"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/salesforce/awd-lstm-lm","reach":{"status":"ok","spdx":"BSD-3-Clause"}}],"summary":{"ran_draft_wrong":1,"ran_honours":2,"unverified":15},"by_repo_kind":{"listed":{"samples":18,"ran":3,"repositories":5}},"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":"1f32d831b2c4c04b","entry":"batchify","repo":"ari-holtzman/genlm","repo_kind":"listed","path":"utils.py","file_url":"https://github.com/ari-holtzman/genlm/blob/HEAD/utils.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"1f32d831b2c4c04b"}},{"code_sha256_prefix":"d38f82da04a3f93e","entry":"one_hot","repo":"AtheMathmo/lookahead-lstm","repo_kind":"listed","path":"pointer.py","file_url":"https://github.com/AtheMathmo/lookahead-lstm/blob/HEAD/pointer.py","link_basis":"plan_row","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"d38f82da04a3f93e"}},{"code_sha256_prefix":"4372bb4533fd1936","entry":"repackage_hidden","repo":"SachinIchake/KALM","repo_kind":"listed","path":"utils.py","file_url":"https://github.com/SachinIchake/KALM/blob/HEAD/utils.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"4372bb4533fd1936"}},{"code_sha256_prefix":"6bd10c3dd56c2b8c","entry":"batchify","repo":"SachinIchake/KALM","repo_kind":"listed","path":"utils.py","file_url":"https://github.com/SachinIchake/KALM/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":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"6bd10c3dd56c2b8c"}},{"code_sha256_prefix":"6696579704cf7e5b","entry":"batchify","repo":"ari-holtzman/genlm","repo_kind":"listed","path":"utils.py","file_url":"https://github.com/ari-holtzman/genlm/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":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"6696579704cf7e5b"}},{"code_sha256_prefix":"ab108d1a1112ff73","entry":"cone_distance","repo":"philippwirth/treelangrnn","repo_kind":"listed","path":"distance.py","file_url":"https://github.com/philippwirth/treelangrnn/blob/HEAD/distance.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"ab108d1a1112ff73"}},{"code_sha256_prefix":"98a55feeff35dab9","entry":"dot_distance","repo":"philippwirth/treelangrnn","repo_kind":"listed","path":"distance.py","file_url":"https://github.com/philippwirth/treelangrnn/blob/HEAD/distance.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"98a55feeff35dab9"}},{"code_sha256_prefix":"62d148258bdd054f","entry":"embedded_dropout","repo":"AtheMathmo/lookahead-lstm","repo_kind":"listed","path":"embed_regularize.py","file_url":"https://github.com/AtheMathmo/lookahead-lstm/blob/HEAD/embed_regularize.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"62d148258bdd054f"}},{"code_sha256_prefix":"89727c8d9972d138","entry":"eucl_distance","repo":"philippwirth/treelangrnn","repo_kind":"listed","path":"distance.py","file_url":"https://github.com/philippwirth/treelangrnn/blob/HEAD/distance.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"89727c8d9972d138"}},{"code_sha256_prefix":"6f3c8e0b36d76af7","entry":"get_batch","repo":"SachinIchake/KALM","repo_kind":"listed","path":"utils.py","file_url":"https://github.com/SachinIchake/KALM/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":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"6f3c8e0b36d76af7"}},{"code_sha256_prefix":"bf412beb331b029b","entry":"hb_atanh","repo":"philippwirth/treelangrnn","repo_kind":"listed","path":"hb_helpers.py","file_url":"https://github.com/philippwirth/treelangrnn/blob/HEAD/hb_helpers.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"bf412beb331b029b"}},{"code_sha256_prefix":"6c36f63c9cd125f4","entry":"hb_project_hyp_vecs","repo":"philippwirth/treelangrnn","repo_kind":"listed","path":"hb_helpers.py","file_url":"https://github.com/philippwirth/treelangrnn/blob/HEAD/hb_helpers.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"6c36f63c9cd125f4"}},{"code_sha256_prefix":"665b5ee8e5d63866","entry":"hp_clip_by_norm","repo":"philippwirth/treelangrnn","repo_kind":"listed","path":"hb_helpers.py","file_url":"https://github.com/philippwirth/treelangrnn/blob/HEAD/hb_helpers.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"665b5ee8e5d63866"}},{"code_sha256_prefix":"bc60fdcf73a9a77f","entry":"log_sigmoid","repo":"philippwirth/treelangrnn","repo_kind":"listed","path":"activation.py","file_url":"https://github.com/philippwirth/treelangrnn/blob/HEAD/activation.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"bc60fdcf73a9a77f"}},{"code_sha256_prefix":"0194ec0fafdf5091","entry":"log_softmax","repo":"philippwirth/treelangrnn","repo_kind":"listed","path":"activation.py","file_url":"https://github.com/philippwirth/treelangrnn/blob/HEAD/activation.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"0194ec0fafdf5091"}},{"code_sha256_prefix":"2e9c943d81e42c08","entry":"make_bnode","repo":"mnhng/hier-char-emb","repo_kind":"listed","path":"nnblk/ids_util.py","file_url":"https://github.com/mnhng/hier-char-emb/blob/HEAD/nnblk/ids_util.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"2e9c943d81e42c08"}},{"code_sha256_prefix":"55bce8b1a136e197","entry":"parse_ids_rules","repo":"mnhng/hier-char-emb","repo_kind":"listed","path":"nnblk/ids_util.py","file_url":"https://github.com/mnhng/hier-char-emb/blob/HEAD/nnblk/ids_util.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"55bce8b1a136e197"}},{"code_sha256_prefix":"311c68b6e9722b88","entry":"var_node","repo":"mnhng/hier-char-emb","repo_kind":"listed","path":"nnblk/ids_util.py","file_url":"https://github.com/mnhng/hier-char-emb/blob/HEAD/nnblk/ids_util.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"311c68b6e9722b88"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}