{"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/exploring-the-limits-of-language-modeling","title":"Exploring the Limits of Language Modeling","arxiv_id":"1602.02410","date":"2016-02-07","proceeding":null,"authors":["Rafal Jozefowicz","Oriol Vinyals","Mike Schuster","Noam Shazeer","Yonghui Wu"],"abstract":"In this work we explore recent advances in Recurrent Neural Networks for\nlarge scale Language Modeling, a task central to language understanding. We\nextend current models to deal with two key challenges present in this task:\ncorpora and vocabulary sizes, and complex, long term structure of language. We\nperform an exhaustive study on techniques such as character Convolutional\nNeural Networks or Long-Short Term Memory, on the One Billion Word Benchmark.\nOur best single model significantly improves state-of-the-art perplexity from\n51.3 down to 30.0 (whilst reducing the number of parameters by a factor of 20),\nwhile an ensemble of models sets a new record by improving perplexity from 41.0\ndown to 23.7. We also release these models for the NLP and ML community to\nstudy and improve upon.","url_abs":"http://arxiv.org/abs/1602.02410v2","url_pdf":"http://arxiv.org/pdf/1602.02410v2.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":"exploring-the-limits-of-language-modeling","repo_url":"https://github.com/DeepMark/deepmark","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"torch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"exploring-the-limits-of-language-modeling","repo_url":"https://github.com/UnofficialJuliaMirror/DeepMark-deepmark","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"torch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"exploring-the-limits-of-language-modeling","repo_url":"https://github.com/UnofficialJuliaMirrorSnapshots/DeepMark-deepmark","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"torch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"exploring-the-limits-of-language-modeling","repo_url":"https://github.com/jmichaelov/does-surprisal-explain-n400","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"exploring-the-limits-of-language-modeling","repo_url":"https://github.com/okuchaiev/f-lm","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"exploring-the-limits-of-language-modeling","repo_url":"https://github.com/rafaljozefowicz/lm","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"exploring-the-limits-of-language-modeling","repo_url":"https://github.com/rdspring1/PyTorch_GBW_LM","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"exploring-the-limits-of-language-modeling","repo_url":"https://github.com/tensorflow/models","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"exploring-the-limits-of-language-modeling","repo_url":"https://github.com/tensorflow/models/tree/master/research/lm_1b","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"exploring-the-limits-of-language-modeling","repo_url":"https://github.com/dmlc/gluon-nlp","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mxnet","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"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-one-billion-word","task":"Language Modelling","dataset":"One Billion Word","model":"10 LSTM+CNN inputs + SNM10-SKIP (ensemble)","rank_in_archive_order":10,"of":27,"metrics":{"Number of params":"43B","PPL":"23.7"},"uses_additional_data":false},{"leaderboard":"/sota/language-modelling-on-one-billion-word","task":"Language Modelling","dataset":"One Billion Word","model":"LSTM-8192-1024 + CNN Input","rank_in_archive_order":18,"of":27,"metrics":{"Number of params":"1.04B","PPL":"30.0"},"uses_additional_data":false},{"leaderboard":"/sota/language-modelling-on-one-billion-word","task":"Language Modelling","dataset":"One Billion Word","model":"LSTM-8192-1024","rank_in_archive_order":19,"of":27,"metrics":{"Number of params":"1.8B","PPL":"30.6"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1602.02410","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1602.02410"}},"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/tensorflow/models","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/rdspring1/PyTorch_GBW_LM","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/tensorflow/models/tree/master/research/lm_1b","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/dmlc/gluon-nlp","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/DeepMark/deepmark","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/UnofficialJuliaMirror/DeepMark-deepmark","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/jmichaelov/does-surprisal-explain-n400","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/UnofficialJuliaMirrorSnapshots/DeepMark-deepmark","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/rafaljozefowicz/lm","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/okuchaiev/f-lm","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_draft_wrong":2,"unverified":6},"by_repo_kind":{"listed":{"samples":8,"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":0,"samples":[{"code_sha256_prefix":"ae7f96f3c9e86ec8","entry":"create_tmux_commands","repo":"rafaljozefowicz/lm","repo_kind":"listed","path":"single_lm_run.py","file_url":"https://github.com/rafaljozefowicz/lm/blob/HEAD/single_lm_run.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"ae7f96f3c9e86ec8"}},{"code_sha256_prefix":"ca384af890f0edff","entry":"new_tmux_cmd","repo":"rafaljozefowicz/lm","repo_kind":"listed","path":"single_lm_run.py","file_url":"https://github.com/rafaljozefowicz/lm/blob/HEAD/single_lm_run.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"ca384af890f0edff"}},{"code_sha256_prefix":"6b2a8f1c93d0b071","entry":"assign_to_gpu","repo":"okuchaiev/f-lm","repo_kind":"listed","path":"common.py","file_url":"https://github.com/okuchaiev/f-lm/blob/HEAD/common.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":"6b2a8f1c93d0b071"}},{"code_sha256_prefix":"909cf81b1c39b724","entry":"find_trainable_variables","repo":"okuchaiev/f-lm","repo_kind":"listed","path":"common.py","file_url":"https://github.com/okuchaiev/f-lm/blob/HEAD/common.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":"909cf81b1c39b724"}},{"code_sha256_prefix":"a5f575756e5a77ed","entry":"getdtype","repo":"okuchaiev/f-lm","repo_kind":"listed","path":"model_utils.py","file_url":"https://github.com/okuchaiev/f-lm/blob/HEAD/model_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":"a5f575756e5a77ed"}},{"code_sha256_prefix":"9aa311876def94db","entry":"linear","repo":"okuchaiev/f-lm","repo_kind":"listed","path":"model_utils.py","file_url":"https://github.com/okuchaiev/f-lm/blob/HEAD/model_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":"9aa311876def94db"}},{"code_sha256_prefix":"3d6b054785523852","entry":"load_from_checkpoint","repo":"okuchaiev/f-lm","repo_kind":"listed","path":"common.py","file_url":"https://github.com/okuchaiev/f-lm/blob/HEAD/common.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":"3d6b054785523852"}},{"code_sha256_prefix":"7045d5e35d2c9925","entry":"sharded_variable","repo":"okuchaiev/f-lm","repo_kind":"listed","path":"model_utils.py","file_url":"https://github.com/okuchaiev/f-lm/blob/HEAD/model_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":"7045d5e35d2c9925"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}