{"id":"https://openalex.org/W2900380465","doi":"https://doi.org/10.3390/e20110839","title":"Cross Entropy of Neural Language Models at Infinity\u2014A New Bound of the Entropy Rate","display_name":"Cross Entropy of Neural Language Models at Infinity\u2014A New Bound of the Entropy Rate","publication_year":2018,"publication_date":"2018-11-02","ids":{"openalex":"https://openalex.org/W2900380465","doi":"https://doi.org/10.3390/e20110839","mag":"2900380465","pmid":"https://pubmed.ncbi.nlm.nih.gov/33266563"},"language":"en","primary_location":{"id":"doi:10.3390/e20110839","is_oa":true,"landing_page_url":"https://doi.org/10.3390/e20110839","pdf_url":"https://www.mdpi.com/1099-4300/20/11/839/pdf?version=1541161858","source":{"id":"https://openalex.org/S195231649","display_name":"Entropy","issn_l":"1099-4300","issn":["1099-4300"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Entropy","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.mdpi.com/1099-4300/20/11/839/pdf?version=1541161858","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5058381648","display_name":"Shuntaro Takahashi","orcid":null},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Shuntaro Takahashi","raw_affiliation_strings":["Graduate School of Frontier Sciences, The University of Tokyo, Chiba 277-8561, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Frontier Sciences, The University of Tokyo, Chiba 277-8561, Japan","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5073822077","display_name":"Kumiko Tanaka\u2010Ishii","orcid":"https://orcid.org/0000-0003-1752-3951"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kumiko Tanaka-Ishii","raw_affiliation_strings":["Research Center for Advanced Science and Technology, The University of Tokyo, Tokyo 153-0041, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Research Center for Advanced Science and Technology, The University of Tokyo, Tokyo 153-0041, Japan","institution_ids":["https://openalex.org/I74801974"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5058381648"],"corresponding_institution_ids":["https://openalex.org/I74801974"],"apc_list":{"value":2000,"currency":"CHF","value_usd":2227},"apc_paid":{"value":2000,"currency":"CHF","value_usd":2227},"fwci":0.7836,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.71123232,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"20","issue":"11","first_page":"839","last_page":"839"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11206","display_name":"Model Reduction and Neural Networks","score":0.9986000061035156,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11206","display_name":"Model Reduction and Neural Networks","score":0.9986000061035156,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10320","display_name":"Neural Networks and Applications","score":0.9975000023841858,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9908000230789185,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.6421394944190979},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.6061521768569946},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5453599691390991},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5110281705856323},{"id":"https://openalex.org/keywords/principle-of-maximum-entropy","display_name":"Principle of maximum entropy","score":0.49425673484802246},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.49336281418800354},{"id":"https://openalex.org/keywords/upper-and-lower-bounds","display_name":"Upper and lower bounds","score":0.48535242676734924},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.42875537276268005},{"id":"https://openalex.org/keywords/statistical-physics","display_name":"Statistical physics","score":0.3956717848777771},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.34694159030914307},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3212320804595947},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.1321929693222046},{"id":"https://openalex.org/keywords/mathematical-analysis","display_name":"Mathematical analysis","score":0.1116509735584259},{"id":"https://openalex.org/keywords/thermodynamics","display_name":"Thermodynamics","score":0.08052211999893188}],"concepts":[{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.6421394944190979},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.6061521768569946},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5453599691390991},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5110281705856323},{"id":"https://openalex.org/C9679016","wikidata":"https://www.wikidata.org/wiki/Q1417473","display_name":"Principle of maximum entropy","level":2,"score":0.49425673484802246},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.49336281418800354},{"id":"https://openalex.org/C77553402","wikidata":"https://www.wikidata.org/wiki/Q13222579","display_name":"Upper and lower bounds","level":2,"score":0.48535242676734924},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42875537276268005},{"id":"https://openalex.org/C121864883","wikidata":"https://www.wikidata.org/wiki/Q677916","display_name":"Statistical physics","level":1,"score":0.3956717848777771},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.34694159030914307},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3212320804595947},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.1321929693222046},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.1116509735584259},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.08052211999893188}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.3390/e20110839","is_oa":true,"landing_page_url":"https://doi.org/10.3390/e20110839","pdf_url":"https://www.mdpi.com/1099-4300/20/11/839/pdf?version=1541161858","source":{"id":"https://openalex.org/S195231649","display_name":"Entropy","issn_l":"1099-4300","issn":["1099-4300"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Entropy","raw_type":"journal-article"},{"id":"pmid:33266563","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/33266563","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Entropy (Basel, Switzerland)","raw_type":null},{"id":"pmh:oai:doaj.org/article:182228ac8962447ca5f3877de8bae9cd","is_oa":false,"landing_page_url":"https://doaj.org/article/182228ac8962447ca5f3877de8bae9cd","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Entropy, Vol 20, Iss 11, p 839 (2018)","raw_type":"article"},{"id":"pmh:oai:mdpi.com:/1099-4300/20/11/839/","is_oa":true,"landing_page_url":"http://dx.doi.org/10.3390/e20110839","pdf_url":null,"source":{"id":"https://openalex.org/S4306400947","display_name":"MDPI (MDPI AG)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210097602","host_organization_name":"Multidisciplinary Digital Publishing Institute (Switzerland)","host_organization_lineage":["https://openalex.org/I4210097602"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Entropy","raw_type":"Text"},{"id":"pmh:oai:pubmedcentral.nih.gov:7512401","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/7512401","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Entropy (Basel)","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.3390/e20110839","is_oa":true,"landing_page_url":"https://doi.org/10.3390/e20110839","pdf_url":"https://www.mdpi.com/1099-4300/20/11/839/pdf?version=1541161858","source":{"id":"https://openalex.org/S195231649","display_name":"Entropy","issn_l":"1099-4300","issn":["1099-4300"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Entropy","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.7799999713897705,"id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G117747529","display_name":"\u8a00\u8a9e\u306e\u8a08\u6e2c\u53ef\u80fd\u306a\u4e0d\u5909\u91cf\u306e\u63a2\u6c42","funder_award_id":"JPMJPR14E5","funder_id":"https://openalex.org/F4320334789","funder_display_name":"Japan Science and Technology Agency"}],"funders":[{"id":"https://openalex.org/F4320334789","display_name":"Japan Science and Technology Agency","ror":"https://ror.org/00097mb19"},{"id":"https://openalex.org/F4320338116","display_name":"Research Institute of Science and Technology for Society","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W104184427","https://openalex.org/W179875071","https://openalex.org/W1610379262","https://openalex.org/W1815076433","https://openalex.org/W1974951348","https://openalex.org/W2018891628","https://openalex.org/W2064675550","https://openalex.org/W2079145130","https://openalex.org/W2086161653","https://openalex.org/W2095705004","https://openalex.org/W2118649542","https://openalex.org/W2132766440","https://openalex.org/W2134237567","https://openalex.org/W2144679335","https://openalex.org/W2149298154","https://openalex.org/W2149741699","https://openalex.org/W2152755776","https://openalex.org/W2180877453","https://openalex.org/W2212703438","https://openalex.org/W2271840356","https://openalex.org/W2323296687","https://openalex.org/W2402274463","https://openalex.org/W2529894091","https://openalex.org/W2611598898","https://openalex.org/W2611669587","https://openalex.org/W2743945814","https://openalex.org/W2767321762","https://openalex.org/W2963951265","https://openalex.org/W3125689392","https://openalex.org/W6626481562","https://openalex.org/W6640281019","https://openalex.org/W6674330103","https://openalex.org/W6682264535","https://openalex.org/W6741459021","https://openalex.org/W6756040250"],"related_works":["https://openalex.org/W2169518243","https://openalex.org/W2938514635","https://openalex.org/W3101314311","https://openalex.org/W4360764540","https://openalex.org/W4231657010","https://openalex.org/W2040052409","https://openalex.org/W2047632477","https://openalex.org/W2158873310","https://openalex.org/W2970690932","https://openalex.org/W2110715801"],"abstract_inverted_index":{"Neural":[0],"language":[1,16,28,32,51,110,114,148],"models":[2,111],"have":[3],"drawn":[4],"a":[5,43,98,102],"lot":[6],"of":[7,26,45,49,81,142,146],"attention":[8],"for":[9,73,105,126],"their":[10],"strong":[11],"ability":[12],"to":[13,133],"predict":[14],"natural":[15,27,147],"text.":[17],"In":[18],"this":[19],"paper,":[20],"we":[21,38,120],"estimate":[22],"the":[23,36,40,46,54,79,82,85,93,118,130,139,143,153],"entropy":[24,95,144],"rate":[25,145],"with":[29,62,101,112],"state-of-the-art":[30,108],"neural":[31,50,109],"models.":[33],"To":[34],"obtain":[35],"estimate,":[37],"consider":[39],"cross":[41,94],"entropy,":[42],"measure":[44],"prediction":[47],"accuracy":[48],"models,":[52],"under":[53],"theoretically":[55],"ideal":[56],"conditions":[57],"that":[58,78,138],"they":[59],"are":[60],"trained":[61],"an":[63,69],"infinitely":[64,70],"large":[65],"dataset":[66],"and":[67,89],"receive":[68],"long":[71],"context":[72,90],"prediction.":[74],"We":[75],"empirically":[76],"verify":[77],"effects":[80],"two":[83,106,131],"parameters,":[84],"training":[86],"data":[87],"size":[88],"length,":[91],"on":[92,117],"consistently":[96],"obey":[97],"power-law":[99],"decay":[100],"positive":[103],"constant":[104],"different":[107,113],"datasets.":[115],"Based":[116],"verification,":[119],"obtained":[121],"1.12":[122],"bits":[123],"per":[124],"character":[125],"English":[127],"by":[128],"extrapolating":[129],"parameters":[132],"infinity.":[134],"This":[135],"result":[136],"suggests":[137],"upper":[140],"bound":[141],"is":[149],"potentially":[150],"smaller":[151],"than":[152],"previously":[154],"reported":[155],"values.":[156]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}