{"id":"https://openalex.org/W2529894091","doi":"https://doi.org/10.3390/e18100364","title":"Entropy Rate Estimates for Natural Language\u2014A New Extrapolation of Compressed Large-Scale Corpora","display_name":"Entropy Rate Estimates for Natural Language\u2014A New Extrapolation of Compressed Large-Scale Corpora","publication_year":2016,"publication_date":"2016-10-12","ids":{"openalex":"https://openalex.org/W2529894091","doi":"https://doi.org/10.3390/e18100364","mag":"2529894091"},"language":"en","primary_location":{"id":"doi:10.3390/e18100364","is_oa":true,"landing_page_url":"https://doi.org/10.3390/e18100364","pdf_url":"https://www.mdpi.com/1099-4300/18/10/364/pdf?version=1476267566","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"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.mdpi.com/1099-4300/18/10/364/pdf?version=1476267566","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5087981690","display_name":"Ryosuke Takahira","orcid":null},"institutions":[{"id":"https://openalex.org/I135598925","display_name":"Kyushu University","ror":"https://ror.org/00p4k0j84","country_code":"JP","type":"education","lineage":["https://openalex.org/I135598925"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Ryosuke Takahira","raw_affiliation_strings":["Graduate School of Information Science and Electrical Engineering, Kyushu University, Fukuoka 819-0395, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Information Science and Electrical Engineering, Kyushu University, Fukuoka 819-0395, Japan","institution_ids":["https://openalex.org/I135598925"]}]},{"author_position":"middle","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":true,"raw_author_name":"Kumiko Tanaka-Ishii","raw_affiliation_strings":["Research Center for Advanced Science and Technology, University of Tokyo, Tokyo 153-8904, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Research Center for Advanced Science and Technology, University of Tokyo, Tokyo 153-8904, Japan","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5076911703","display_name":"\u0141ukasz D\u0119bowski","orcid":"https://orcid.org/0000-0001-7136-5283"},"institutions":[{"id":"https://openalex.org/I4210087266","display_name":"Institute of Computer Science","ror":"https://ror.org/003fvp964","country_code":"PL","type":"facility","lineage":["https://openalex.org/I4210087266","https://openalex.org/I99542240"]},{"id":"https://openalex.org/I99542240","display_name":"Polish Academy of Sciences","ror":"https://ror.org/01dr6c206","country_code":"PL","type":"government","lineage":["https://openalex.org/I99542240"]}],"countries":["PL"],"is_corresponding":false,"raw_author_name":"\u0141ukasz D\u0119bowski","raw_affiliation_strings":["Institute of Computer Science, Polish Academy of Sciences, Warszawa 01-248, Poland"],"raw_orcid":"https://orcid.org/0000-0001-7136-5283","affiliations":[{"raw_affiliation_string":"Institute of Computer Science, Polish Academy of Sciences, Warszawa 01-248, Poland","institution_ids":["https://openalex.org/I4210087266","https://openalex.org/I99542240"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5073822077"],"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":9.3266,"has_fulltext":false,"cited_by_count":56,"citation_normalized_percentile":{"value":0.97610274,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"18","issue":"10","first_page":"364","last_page":"364"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.9988999962806702,"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"}},"topics":[{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.9988999962806702,"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/T12946","display_name":"Fractal and DNA sequence analysis","score":0.9952999949455261,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T12254","display_name":"Machine Learning in Bioinformatics","score":0.9919000267982483,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/extrapolation","display_name":"Extrapolation","score":0.860076904296875},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.6297661066055298},{"id":"https://openalex.org/keywords/ansatz","display_name":"Ansatz","score":0.6079280376434326},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.5711178183555603},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.4958711564540863},{"id":"https://openalex.org/keywords/exponential-function","display_name":"Exponential function","score":0.48676490783691406},{"id":"https://openalex.org/keywords/statistical-physics","display_name":"Statistical physics","score":0.4382120370864868},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.40018197894096375},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.3640126585960388},{"id":"https://openalex.org/keywords/econometrics","display_name":"Econometrics","score":0.3347323536872864},{"id":"https://openalex.org/keywords/applied-mathematics","display_name":"Applied mathematics","score":0.3243739604949951},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.27924537658691406},{"id":"https://openalex.org/keywords/mathematical-analysis","display_name":"Mathematical analysis","score":0.16823041439056396},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.13542890548706055},{"id":"https://openalex.org/keywords/thermodynamics","display_name":"Thermodynamics","score":0.12148311734199524}],"concepts":[{"id":"https://openalex.org/C132459708","wikidata":"https://www.wikidata.org/wiki/Q744069","display_name":"Extrapolation","level":2,"score":0.860076904296875},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.6297661066055298},{"id":"https://openalex.org/C130979935","wikidata":"https://www.wikidata.org/wiki/Q568954","display_name":"Ansatz","level":2,"score":0.6079280376434326},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.5711178183555603},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.4958711564540863},{"id":"https://openalex.org/C151376022","wikidata":"https://www.wikidata.org/wiki/Q168698","display_name":"Exponential function","level":2,"score":0.48676490783691406},{"id":"https://openalex.org/C121864883","wikidata":"https://www.wikidata.org/wiki/Q677916","display_name":"Statistical physics","level":1,"score":0.4382120370864868},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.40018197894096375},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.3640126585960388},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.3347323536872864},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.3243739604949951},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.27924537658691406},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.16823041439056396},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.13542890548706055},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.12148311734199524},{"id":"https://openalex.org/C37914503","wikidata":"https://www.wikidata.org/wiki/Q156495","display_name":"Mathematical physics","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.3390/e18100364","is_oa":true,"landing_page_url":"https://doi.org/10.3390/e18100364","pdf_url":"https://www.mdpi.com/1099-4300/18/10/364/pdf?version=1476267566","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":"pmh:oai:doaj.org/article:c5e79bbc3e8f4ec681f86cfc208bcba5","is_oa":true,"landing_page_url":"https://doaj.org/article/c5e79bbc3e8f4ec681f86cfc208bcba5","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":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Entropy, Vol 18, Iss 10, p 364 (2016)","raw_type":"article"},{"id":"pmh:oai:mdpi.com:/1099-4300/18/10/364/","is_oa":true,"landing_page_url":"https://dx.doi.org/10.3390/e18100364","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; Volume 18; Issue 10; Pages: 364","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.3390/e18100364","is_oa":true,"landing_page_url":"https://doi.org/10.3390/e18100364","pdf_url":"https://www.mdpi.com/1099-4300/18/10/364/pdf?version=1476267566","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":[{"id":"https://metadata.un.org/sdg/4","score":0.8299999833106995,"display_name":"Quality Education"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320334789","display_name":"Japan Science and Technology Agency","ror":"https://ror.org/00097mb19"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W1489380330","https://openalex.org/W1532729789","https://openalex.org/W1594577007","https://openalex.org/W1610379262","https://openalex.org/W1930176176","https://openalex.org/W1962301972","https://openalex.org/W1968884246","https://openalex.org/W1974951348","https://openalex.org/W1985556836","https://openalex.org/W1995875735","https://openalex.org/W2018891628","https://openalex.org/W2033634113","https://openalex.org/W2063523065","https://openalex.org/W2079145130","https://openalex.org/W2093428076","https://openalex.org/W2096465081","https://openalex.org/W2099111195","https://openalex.org/W2102098892","https://openalex.org/W2102573550","https://openalex.org/W2105686649","https://openalex.org/W2107745473","https://openalex.org/W2113110240","https://openalex.org/W2115054880","https://openalex.org/W2130956967","https://openalex.org/W2134211228","https://openalex.org/W2144679335","https://openalex.org/W2149741699","https://openalex.org/W2157365695","https://openalex.org/W2162761290","https://openalex.org/W2163294786","https://openalex.org/W2291528757","https://openalex.org/W2323296687","https://openalex.org/W2329003026","https://openalex.org/W3100091869","https://openalex.org/W3102114848","https://openalex.org/W4245687973","https://openalex.org/W6682264535"],"related_works":["https://openalex.org/W1968270095","https://openalex.org/W2089909466","https://openalex.org/W2220129715","https://openalex.org/W4296478327","https://openalex.org/W2042397106","https://openalex.org/W4361730764","https://openalex.org/W1965029248","https://openalex.org/W2333625343","https://openalex.org/W1960072520","https://openalex.org/W4389727978"],"abstract_inverted_index":{"One":[0],"of":[1,22,33,53,66,128,137,161,177,187],"the":[2,19,31,84,91,134,150,156,159,162,175],"fundamental":[3],"questions":[4],"about":[5,30],"human":[6,138],"language":[7,34,179],"is":[8,13,87],"whether":[9],"its":[10],"entropy":[11,16,32,85,135,151],"rate":[12,17,86,152],"positive.":[14,88],"The":[15,28],"measures":[18],"average":[20],"amount":[21],"information":[23],"communicated":[24],"per":[25],"unit":[26],"time.":[27],"question":[29],"dates":[35],"back":[36],"to":[37,68,81,97,167,195],"experiments":[38],"by":[39,105],"Shannon":[40],"in":[41,44,180,185],"1951,":[42],"but":[43,142],"1990":[45],"Hilberg":[46],"raised":[47],"doubt":[48],"regarding":[49],"a":[50,117,125],"correct":[51],"interpretation":[52],"these":[54],"experiments.":[55],"This":[56],"article":[57],"provides":[58],"an":[59,101,106],"in-depth":[60],"empirical":[61],"analysis,":[62],"using":[63],"20":[64],"corpora":[65],"up":[67],"7.8":[69],"gigabytes":[70],"across":[71,170],"six":[72],"languages":[73,139,172,191],"(English,":[74],"French,":[75],"Russian,":[76],"Korean,":[77],"Chinese,":[78],"and":[79,173],"Japanese),":[80],"conclude":[82,132],"that":[83,123,133],"To":[89],"obtain":[90],"estimates":[92,153],"for":[93],"data":[94],"length":[95],"tending":[96],"infinity,":[98],"we":[99,115,131],"use":[100,116],"extrapolation":[102,121],"function":[103,122,164],"given":[104],"ansatz.":[107],"Whereas":[108],"some":[109],"ansatzes":[110],"were":[111],"proposed":[112],"previously,":[113],"here":[114],"new":[118],"stretched":[119],"exponential":[120],"has":[124],"smaller":[126,145],"error":[127],"fit.":[129],"Thus,":[130],"rates":[136],"are":[140],"positive":[141],"approximately":[143],"20%":[144],"than":[146],"without":[147],"extrapolation.":[148],"Although":[149],"depend":[154],"on":[155],"script":[157],"kind,":[158],"exponent":[160],"ansatz":[163],"turns":[165],"out":[166],"be":[168],"constant":[169],"different":[171],"governs":[174],"complexity":[176],"natural":[178],"general.":[181],"In":[182],"other":[183],"words,":[184],"spite":[186],"typological":[188],"differences,":[189],"all":[190],"seem":[192],"equally":[193],"hard":[194],"learn,":[196],"which":[197],"partly":[198],"confirms":[199],"Hilberg\u2019s":[200],"hypothesis.":[201]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":9},{"year":2022,"cited_by_count":9},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":6},{"year":2019,"cited_by_count":6},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":7},{"year":2016,"cited_by_count":1}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2016-10-21T00:00:00"}