{"id":"https://openalex.org/W2611598898","doi":"https://doi.org/10.3390/e19060275","title":"The Entropy of Words\u2014Learnability and Expressivity across More than 1000 Languages","display_name":"The Entropy of Words\u2014Learnability and Expressivity across More than 1000 Languages","publication_year":2017,"publication_date":"2017-06-14","ids":{"openalex":"https://openalex.org/W2611598898","doi":"https://doi.org/10.3390/e19060275","mag":"2611598898"},"language":"en","primary_location":{"id":"doi:10.3390/e19060275","is_oa":true,"landing_page_url":"https://doi.org/10.3390/e19060275","pdf_url":"https://www.mdpi.com/1099-4300/19/6/275/pdf?version=1497446649","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/1099-4300/19/6/275/pdf?version=1497446649","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5059804119","display_name":"Christian Bentz","orcid":"https://orcid.org/0000-0001-6570-9326"},"institutions":[{"id":"https://openalex.org/I8087733","display_name":"University of T\u00fcbingen","ror":"https://ror.org/03a1kwz48","country_code":"DE","type":"education","lineage":["https://openalex.org/I8087733"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Christian Bentz","raw_affiliation_strings":["DFG Center for Advanced Studies, University of T\u00fcbingen, R\u00fcmelinstra\u00dfe 23, D-72070 T\u00fcbingen, Germany","Department of General Linguistics, University of T\u00fcbingen, Wilhemstra\u00dfe 19-23, D-72074 T\u00fcbingen, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DFG Center for Advanced Studies, University of T\u00fcbingen, R\u00fcmelinstra\u00dfe 23, D-72070 T\u00fcbingen, Germany","institution_ids":["https://openalex.org/I8087733"]},{"raw_affiliation_string":"Department of General Linguistics, University of T\u00fcbingen, Wilhemstra\u00dfe 19-23, D-72074 T\u00fcbingen, Germany","institution_ids":["https://openalex.org/I8087733"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012895040","display_name":"Dimitrios Alikaniotis","orcid":null},"institutions":[{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Dimitrios Alikaniotis","raw_affiliation_strings":["Department of Theoretical and Applied Linguistics, University of Cambridge, Cambridge CB3 9DP, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Theoretical and Applied Linguistics, University of Cambridge, Cambridge CB3 9DP, UK","institution_ids":["https://openalex.org/I241749"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027057380","display_name":"Michael Cysouw","orcid":"https://orcid.org/0000-0003-3168-4946"},"institutions":[{"id":"https://openalex.org/I161103922","display_name":"Philipps University of Marburg","ror":"https://ror.org/01rdrb571","country_code":"DE","type":"education","lineage":["https://openalex.org/I161103922"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Michael Cysouw","raw_affiliation_strings":["Forschungszentrum Deutscher Sprachatlas, Philipps-Universit\u00e4t Marburg, Pilgrimstein 16, D-35032 Marburg, Germany"],"raw_orcid":"https://orcid.org/0000-0003-3168-4946","affiliations":[{"raw_affiliation_string":"Forschungszentrum Deutscher Sprachatlas, Philipps-Universit\u00e4t Marburg, Pilgrimstein 16, D-35032 Marburg, Germany","institution_ids":["https://openalex.org/I161103922"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5014322193","display_name":"Ramon Ferrer\u2010i\u2010Cancho","orcid":"https://orcid.org/0000-0002-7820-923X"},"institutions":[{"id":"https://openalex.org/I9617848","display_name":"Universitat Polit\u00e8cnica de Catalunya","ror":"https://ror.org/03mb6wj31","country_code":"ES","type":"education","lineage":["https://openalex.org/I9617848"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Ramon Ferrer-i-Cancho","raw_affiliation_strings":["Complexity and Quantitative Linguistics Lab, LARCA Research Group, Departament de Ci\u00e8ncies de la Computaci\u00f3, Universitat Polit\u00e8cnica de Catalunya, 08034 Barcelona, Catalonia, Spain"],"raw_orcid":"https://orcid.org/0000-0002-7820-923X","affiliations":[{"raw_affiliation_string":"Complexity and Quantitative Linguistics Lab, LARCA Research Group, Departament de Ci\u00e8ncies de la Computaci\u00f3, Universitat Polit\u00e8cnica de Catalunya, 08034 Barcelona, Catalonia, Spain","institution_ids":["https://openalex.org/I9617848"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5059804119"],"corresponding_institution_ids":["https://openalex.org/I8087733"],"apc_list":{"value":2000,"currency":"CHF","value_usd":2227},"apc_paid":{"value":1233,"currency":"EUR","value_usd":1329},"fwci":7.4973,"has_fulltext":true,"cited_by_count":119,"citation_normalized_percentile":{"value":0.97556574,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":"19","issue":"6","first_page":"275","last_page":"275"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12380","display_name":"Authorship Attribution and Profiling","score":0.9890999794006348,"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/T12380","display_name":"Authorship Attribution and Profiling","score":0.9890999794006348,"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/T12090","display_name":"Language and cultural evolution","score":0.9868000149726868,"subfield":{"id":"https://openalex.org/subfields/3316","display_name":"Cultural Studies"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12254","display_name":"Machine Learning in Bioinformatics","score":0.9866999983787537,"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/learnability","display_name":"Learnability","score":0.699256181716919},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6322357654571533},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5824064016342163},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.56513911485672},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.5100539326667786},{"id":"https://openalex.org/keywords/information-theory","display_name":"Information theory","score":0.4162311255931854},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.395143985748291},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.3045021891593933},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.13210341334342957}],"concepts":[{"id":"https://openalex.org/C2777723229","wikidata":"https://www.wikidata.org/wiki/Q4367921","display_name":"Learnability","level":2,"score":0.699256181716919},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6322357654571533},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5824064016342163},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.56513911485672},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.5100539326667786},{"id":"https://openalex.org/C52622258","wikidata":"https://www.wikidata.org/wiki/Q131222","display_name":"Information theory","level":2,"score":0.4162311255931854},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.395143985748291},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3045021891593933},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.13210341334342957},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.3390/e19060275","is_oa":true,"landing_page_url":"https://doi.org/10.3390/e19060275","pdf_url":"https://www.mdpi.com/1099-4300/19/6/275/pdf?version=1497446649","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:upcommons.upc.edu:2117/106703","is_oa":true,"landing_page_url":"https://hdl.handle.net/2117/106703","pdf_url":null,"source":{"id":"https://openalex.org/S4377196262","display_name":"UPCommons institutional repository (Universitat Polit\u00e8cnica de Catalunya)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I9617848","host_organization_name":"Universitat Polit\u00e8cnica de Catalunya","host_organization_lineage":["https://openalex.org/I9617848"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"Article"},{"id":"pmh:oai:doaj.org/article:e064ee69622b4a11bd0974a8297af484","is_oa":true,"landing_page_url":"https://doaj.org/article/e064ee69622b4a11bd0974a8297af484","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 19, Iss 6, p 275 (2017)","raw_type":"article"},{"id":"pmh:oai:mdpi.com:/1099-4300/19/6/275/","is_oa":true,"landing_page_url":"https://dx.doi.org/10.3390/e19060275","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 19; Issue 6; Pages: 275","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.3390/e19060275","is_oa":true,"landing_page_url":"https://doi.org/10.3390/e19060275","pdf_url":"https://www.mdpi.com/1099-4300/19/6/275/pdf?version=1497446649","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":0.8500000238418579,"display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G1090126505","display_name":null,"funder_award_id":"2014SGR 890","funder_id":"https://openalex.org/F4320321505","funder_display_name":"Generalitat de Catalunya"},{"id":"https://openalex.org/G28439736","display_name":null,"funder_award_id":"DFG\u2010FOR 2237","funder_id":"https://openalex.org/F4320320879","funder_display_name":"Deutsche Forschungsgemeinschaft"},{"id":"https://openalex.org/G5207488495","display_name":null,"funder_award_id":"FOR2237","funder_id":"https://openalex.org/F4320320879","funder_display_name":"Deutsche Forschungsgemeinschaft"},{"id":"https://openalex.org/G6605718524","display_name":null,"funder_award_id":"2014SGR 890","funder_id":"https://openalex.org/F4320334830","funder_display_name":"Ag\u00e8ncia de Gesti\u00f3 d'Ajuts Universitaris i de Recerca"},{"id":"https://openalex.org/G985971609","display_name":null,"funder_award_id":"2014SGR","funder_id":"https://openalex.org/F4320321505","funder_display_name":"Generalitat de Catalunya"}],"funders":[{"id":"https://openalex.org/F4320320879","display_name":"Deutsche Forschungsgemeinschaft","ror":"https://ror.org/018mejw64"},{"id":"https://openalex.org/F4320321505","display_name":"Generalitat de Catalunya","ror":"https://ror.org/01bg62x04"},{"id":"https://openalex.org/F4320334830","display_name":"Ag\u00e8ncia de Gesti\u00f3 d'Ajuts Universitaris i de Recerca","ror":"https://ror.org/01n4pqe45"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2611598898.pdf","grobid_xml":"https://content.openalex.org/works/W2611598898.grobid-xml"},"referenced_works_count":87,"referenced_works":["https://openalex.org/W22168010","https://openalex.org/W564535476","https://openalex.org/W636189409","https://openalex.org/W1498437823","https://openalex.org/W1516339661","https://openalex.org/W1521255875","https://openalex.org/W1548184736","https://openalex.org/W1566144976","https://openalex.org/W1617429671","https://openalex.org/W1764875147","https://openalex.org/W1951724000","https://openalex.org/W1979135380","https://openalex.org/W1980469977","https://openalex.org/W1989151402","https://openalex.org/W1993909881","https://openalex.org/W1995875735","https://openalex.org/W2002072840","https://openalex.org/W2008203686","https://openalex.org/W2009047999","https://openalex.org/W2009643512","https://openalex.org/W2010254479","https://openalex.org/W2017163068","https://openalex.org/W2018891628","https://openalex.org/W2022564164","https://openalex.org/W2027321393","https://openalex.org/W2027933821","https://openalex.org/W2030475414","https://openalex.org/W2036611122","https://openalex.org/W2038542953","https://openalex.org/W2060590556","https://openalex.org/W2079145130","https://openalex.org/W2079473986","https://openalex.org/W2090618725","https://openalex.org/W2096175520","https://openalex.org/W2097173970","https://openalex.org/W2105286578","https://openalex.org/W2107745473","https://openalex.org/W2108717659","https://openalex.org/W2115054880","https://openalex.org/W2117805756","https://openalex.org/W2118232585","https://openalex.org/W2118260303","https://openalex.org/W2122962290","https://openalex.org/W2127516329","https://openalex.org/W2129955048","https://openalex.org/W2134211228","https://openalex.org/W2135191607","https://openalex.org/W2147962921","https://openalex.org/W2149741699","https://openalex.org/W2154124206","https://openalex.org/W2163529839","https://openalex.org/W2164418233","https://openalex.org/W2165854268","https://openalex.org/W2171250734","https://openalex.org/W2171951705","https://openalex.org/W2250523604","https://openalex.org/W2251981022","https://openalex.org/W2252016195","https://openalex.org/W2294701801","https://openalex.org/W2336061621","https://openalex.org/W2401701515","https://openalex.org/W2411726009","https://openalex.org/W2489774063","https://openalex.org/W2509530726","https://openalex.org/W2510474575","https://openalex.org/W2529894091","https://openalex.org/W2595996756","https://openalex.org/W2596532918","https://openalex.org/W2611951478","https://openalex.org/W2731305122","https://openalex.org/W2963625738","https://openalex.org/W3098115713","https://openalex.org/W3099460613","https://openalex.org/W3101351113","https://openalex.org/W3102114848","https://openalex.org/W3104836896","https://openalex.org/W4206415992","https://openalex.org/W6604337958","https://openalex.org/W6632812989","https://openalex.org/W6652434780","https://openalex.org/W6674650171","https://openalex.org/W6674669923","https://openalex.org/W6679705636","https://openalex.org/W6682264535","https://openalex.org/W6687793582","https://openalex.org/W6696447242","https://openalex.org/W6714758027"],"related_works":["https://openalex.org/W2061278088","https://openalex.org/W2075237332","https://openalex.org/W2163103544","https://openalex.org/W3039080452","https://openalex.org/W3033899355","https://openalex.org/W3025482071","https://openalex.org/W4210452449","https://openalex.org/W2921877942","https://openalex.org/W2055254734","https://openalex.org/W2889544313"],"abstract_inverted_index":{"The":[0,172],"choice":[1,41],"associated":[2,42],"with":[3,43,116,132,153,177],"words":[4,58,93,176,200],"is":[5,110,129,161,182],"a":[6,117,141,154,162],"fundamental":[7,146],"property":[8],"of":[9,17,40,68,75,92,120,135,199,208],"natural":[10],"languages.":[11],"It":[12],"lies":[13],"at":[14,32],"the":[15,37,45,69,193,197,203,209],"heart":[16],"quantitative":[18],"linguistics,":[19],"computational":[20],"linguistics":[21],"and":[22,62,72,85,150,169,178],"language":[23,112],"sciences":[24],"more":[25],"generally.":[26],"Information":[27],"theory":[28],"gives":[29],"us":[30],"tools":[31],"hand":[33],"to":[34,65],"measure":[35],"precisely":[36],"average":[38],"amount":[39,205],"words:":[44],"word":[46,76,102,148,151],"entropy.":[47],"Here,":[48],"we":[49],"use":[50],"three":[51,187],"parallel":[52],"corpora,":[53],"encompassing":[54],"ca.":[55,186],"450":[56],"million":[57],"in":[59,94,113,130,140],"1916":[60],"texts":[61],"1259":[63],"languages,":[64],"tackle":[66],"some":[67],"major":[70],"conceptual":[71],"practical":[73],"problems":[74],"entropy":[77,119,170,173],"estimation:":[78],"dependence":[79],"on":[80],"text":[81,195],"size,":[82],"register,":[83],"style":[84],"estimation":[86],"method,":[87],"as":[88,90],"well":[89],"non-independence":[91],"co-text.":[95],"We":[96,125],"present":[97],"two":[98,145],"main":[99],"findings:":[100],"Firstly,":[101],"entropies":[103,168],"display":[104],"relatively":[105],"narrow,":[106],"unimodal":[107],"distributions.":[108],"There":[109],"no":[111],"our":[114],"sample":[115],"unigram":[118,167],"less":[121],"than":[122],"six":[123],"bits/word.":[124,188],"argue":[126],"that":[127],"this":[128],"line":[131],"information-theoretic":[133],"models":[134],"communication.":[136],"Languages":[137],"are":[138],"held":[139],"narrow":[142],"range":[143],"by":[144,201],"pressures:":[147],"learnability":[149],"expressivity,":[152],"potential":[155],"bias":[156],"towards":[157],"expressivity.":[158],"Secondly,":[159],"there":[160],"strong":[163],"linear":[164],"relationship":[165],"between":[166,175],"rates.":[171],"difference":[174],"without":[179],"co-textual":[180],"information":[181],"narrowly":[183],"distributed":[184],"around":[185],"In":[189],"other":[190],"words,":[191],"knowing":[192],"preceding":[194],"reduces":[196],"uncertainty":[198],"roughly":[202],"same":[204],"across":[206],"languages":[207],"world.":[210]},"counts_by_year":[{"year":2026,"cited_by_count":11},{"year":2025,"cited_by_count":14},{"year":2024,"cited_by_count":13},{"year":2023,"cited_by_count":17},{"year":2022,"cited_by_count":16},{"year":2021,"cited_by_count":15},{"year":2020,"cited_by_count":12},{"year":2019,"cited_by_count":14},{"year":2018,"cited_by_count":5},{"year":2017,"cited_by_count":2}],"updated_date":"2026-08-11T07:18:39.950985","created_date":"2025-10-10T00:00:00"}