{"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/pointer-sentinel-mixture-models","title":"Pointer Sentinel Mixture Models","arxiv_id":"1609.07843","date":"2016-09-26","proceeding":null,"authors":["Stephen Merity","Caiming Xiong","James Bradbury","Richard Socher"],"abstract":"Recent neural network sequence models with softmax classifiers have achieved\ntheir best language modeling performance only with very large hidden states and\nlarge vocabularies. Even then they struggle to predict rare or unseen words\neven if the context makes the prediction unambiguous. We introduce the pointer\nsentinel mixture architecture for neural sequence models which has the ability\nto either reproduce a word from the recent context or produce a word from a\nstandard softmax classifier. Our pointer sentinel-LSTM model achieves state of\nthe art language modeling performance on the Penn Treebank (70.9 perplexity)\nwhile using far fewer parameters than a standard softmax LSTM. In order to\nevaluate how well language models can exploit longer contexts and deal with\nmore realistic vocabularies and larger corpora we also introduce the freely\navailable WikiText corpus.","url_abs":"http://arxiv.org/abs/1609.07843v1","url_pdf":"http://arxiv.org/pdf/1609.07843v1.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":"pointer-sentinel-mixture-models","repo_url":"https://github.com/axiomlab/Cable","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"pointer-sentinel-mixture-models","repo_url":"https://github.com/elanmart/psmm","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"pointer-sentinel-mixture-models","repo_url":"https://github.com/emanjavacas/pie","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"pointer-sentinel-mixture-models","repo_url":"https://github.com/jfisher52/influence_theory","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"pointer-sentinel-mixture-models","repo_url":"https://github.com/kafura-kafiri/tf2-elmo","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"pointer-sentinel-mixture-models","repo_url":"https://github.com/kkirchheim/pytorch-ood","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"pointer-sentinel-mixture-models","repo_url":"https://github.com/mikekestemont/pie","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"pointer-sentinel-mixture-models","repo_url":"https://github.com/pasta41/deception","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"pointer-sentinel-mixture-models","repo_url":"https://github.com/yangrui123/Hidden","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"pointer-sentinel-mixture-models","repo_url":"https://github.com/zhongping-zhang/engine","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"}],"methods":[{"method_slug":"lstm","method_name":"LSTM"},{"method_slug":"pointer-net","method_name":"Pointer Network"},{"method_slug":"pointer-sentinel-lstm","method_name":"Pointer Sentinel-LSTM"},{"method_slug":"sigmoid-activation","method_name":"Sigmoid Activation"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"tanh-activation","method_name":"Tanh Activation"},{"method_slug":"variational-dropout","method_name":"Variational Dropout"},{"method_slug":"zoneout","method_name":"Zoneout"}],"datasets_introduced":[{"slug":"wikitext-103","name":"WikiText-103","full_name":"WikiText-103"},{"slug":"wikitext-2","name":"WikiText-2","full_name":"WikiText-2"}],"methods_introduced":[{"slug":"pointer-sentinel-lstm","name":"Pointer Sentinel-LSTM","full_name":"Pointer Sentinel-LSTM"}],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1609.07843","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1609.07843"}},"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/pasta41/deception","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/yangrui123/Hidden","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/kkirchheim/pytorch-ood","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/jfisher52/influence_theory","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/emanjavacas/pie","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/kafura-kafiri/tf2-elmo","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/elanmart/psmm","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/zhongping-zhang/engine","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/axiomlab/Cable","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/mikekestemont/pie","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_fixture":1,"ran":1,"unverified":7},"by_repo_kind":{"listed":{"samples":9,"ran":2,"repositories":3}},"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":1,"samples":[{"code_sha256_prefix":"0414551c62a09f12","entry":"DotScorer","repo":"emanjavacas/pie","repo_kind":"listed","path":"pie/models/decoder.py","file_url":"https://github.com/emanjavacas/pie/blob/HEAD/pie/models/decoder.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"0414551c62a09f12"}},{"code_sha256_prefix":"f9fe5f4ff2349a26","entry":"PointerSentinel","repo":"elanmart/psmm","repo_kind":"listed","path":"psmm/model.py","file_url":"https://github.com/elanmart/psmm/blob/HEAD/psmm/model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"f9fe5f4ff2349a26"}},{"code_sha256_prefix":"48e865d17f832cf9","entry":"Attention","repo":"emanjavacas/pie","repo_kind":"listed","path":"pie/models/decoder.py","file_url":"https://github.com/emanjavacas/pie/blob/HEAD/pie/models/decoder.py","link_basis":"first_harvest_node","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":"48e865d17f832cf9"}},{"code_sha256_prefix":"a23814ddbf05037d","entry":"AttentionalDecoder","repo":"emanjavacas/pie","repo_kind":"listed","path":"pie/models/decoder.py","file_url":"https://github.com/emanjavacas/pie/blob/HEAD/pie/models/decoder.py","link_basis":"first_harvest_node","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":"a23814ddbf05037d"}},{"code_sha256_prefix":"99b391f7c6bb9f4c","entry":"BahdanauScorer","repo":"emanjavacas/pie","repo_kind":"listed","path":"pie/models/decoder.py","file_url":"https://github.com/emanjavacas/pie/blob/HEAD/pie/models/decoder.py","link_basis":"first_harvest_node","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":"99b391f7c6bb9f4c"}},{"code_sha256_prefix":"53b424349970dcd4","entry":"Beam","repo":"emanjavacas/pie","repo_kind":"listed","path":"pie/models/decoder.py","file_url":"https://github.com/emanjavacas/pie/blob/HEAD/pie/models/decoder.py","link_basis":"first_harvest_node","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":"53b424349970dcd4"}},{"code_sha256_prefix":"94e662f236fb57ff","entry":"GeneralScorer","repo":"emanjavacas/pie","repo_kind":"listed","path":"pie/models/decoder.py","file_url":"https://github.com/emanjavacas/pie/blob/HEAD/pie/models/decoder.py","link_basis":"first_harvest_node","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":"94e662f236fb57ff"}},{"code_sha256_prefix":"4ee2cb07bb0ad310","entry":"get_known_and_ambigous_tokens","repo":"mikekestemont/pie","repo_kind":"listed","path":"pie/models/scorer.py","file_url":"https://github.com/mikekestemont/pie/blob/HEAD/pie/models/scorer.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":"4ee2cb07bb0ad310"}},{"code_sha256_prefix":"68f526c834cab2f3","entry":"get_pretrained_embeddings","repo":"mikekestemont/pie","repo_kind":"listed","path":"pie/models/loaders.py","file_url":"https://github.com/mikekestemont/pie/blob/HEAD/pie/models/loaders.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":"68f526c834cab2f3"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}