{"id":"https://openalex.org/W2948068983","doi":"https://doi.org/10.1080/09296174.2020.1778387","title":"Optimal Coding and the Origins of Zipfian Laws","display_name":"Optimal Coding and the Origins of Zipfian Laws","publication_year":2020,"publication_date":"2020-07-24","ids":{"openalex":"https://openalex.org/W2948068983","doi":"https://doi.org/10.1080/09296174.2020.1778387","mag":"2948068983"},"language":"en","primary_location":{"id":"doi:10.1080/09296174.2020.1778387","is_oa":false,"landing_page_url":"https://doi.org/10.1080/09296174.2020.1778387","pdf_url":null,"source":{"id":"https://openalex.org/S24321443","display_name":"Journal of Quantitative Linguistics","issn_l":"0929-6174","issn":["0929-6174","1744-5035"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319847","host_organization_name":"Routledge","host_organization_lineage":["https://openalex.org/P4310319847"],"host_organization_lineage_names":["Routledge"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Quantitative Linguistics","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1906.01545","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Ramon Ferrer-i-Cancho","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":true,"raw_author_name":"Ramon Ferrer-i-Cancho","raw_affiliation_strings":["Complexity & Quantitative Linguistics Lab, LARCA Research Group, Departament de Ci\u00e8ncies de la Computaci\u00f3, Universitat Polit\u00e8cnica de Catalunya, Barcelona, Spain"],"affiliations":[{"raw_affiliation_string":"Complexity & Quantitative Linguistics Lab, LARCA Research Group, Departament de Ci\u00e8ncies de la Computaci\u00f3, Universitat Polit\u00e8cnica de Catalunya, Barcelona, Spain","institution_ids":["https://openalex.org/I9617848"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Christian Bentz","orcid":"https://orcid.org/0000-0001-6570-9326"},"institutions":[{"id":"https://openalex.org/I202697423","display_name":"University of Zurich","ror":"https://ror.org/02crff812","country_code":"CH","type":"education","lineage":["https://openalex.org/I202697423"]},{"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":["CH","DE"],"is_corresponding":false,"raw_author_name":"Christian Bentz","raw_affiliation_strings":["DFG Center for Advanced Studies \u201cWords, Bones, Genes, Tools\u201d, University of T\u00fcbingen, T\u00fcbingen, Germany","URPP Language and Space, University of Z\u00fcrich, Z\u00fcrich, Switzerland"],"affiliations":[{"raw_affiliation_string":"DFG Center for Advanced Studies \u201cWords, Bones, Genes, Tools\u201d, University of T\u00fcbingen, T\u00fcbingen, Germany","institution_ids":["https://openalex.org/I8087733"]},{"raw_affiliation_string":"URPP Language and Space, University of Z\u00fcrich, Z\u00fcrich, Switzerland","institution_ids":["https://openalex.org/I202697423"]}]},{"author_position":"last","author":{"id":null,"display_name":"Caio Seguin","orcid":"https://orcid.org/0000-0001-9384-6336"},"institutions":[{"id":"https://openalex.org/I165779595","display_name":"The University of Melbourne","ror":"https://ror.org/01ej9dk98","country_code":"AU","type":"education","lineage":["https://openalex.org/I165779595"]},{"id":"https://openalex.org/I4210158168","display_name":"Melbourne Health","ror":"https://ror.org/04z4kmw33","country_code":"AU","type":"healthcare","lineage":["https://openalex.org/I4210158168"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Caio Seguin","raw_affiliation_strings":["Melbourne Neuropsychiatry Centre, The University of Melbourne and Melbourne Health, Melbourne, Australia"],"affiliations":[{"raw_affiliation_string":"Melbourne Neuropsychiatry Centre, The University of Melbourne and Melbourne Health, Melbourne, Australia","institution_ids":["https://openalex.org/I4210158168","https://openalex.org/I165779595"]}]}],"institutions":[],"countries_distinct_count":4,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I9617848"],"apc_list":null,"apc_paid":null,"fwci":8.7001,"has_fulltext":false,"cited_by_count":84,"citation_normalized_percentile":{"value":0.98198825,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":"29","issue":"2","first_page":"165","last_page":"194"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.2590999901294708,"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":0.2590999901294708,"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/T12002","display_name":"Computability, Logic, AI Algorithms","score":0.13079999387264252,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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":0.11840000003576279,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/shannon\u2013fano-coding","display_name":"Shannon\u2013Fano coding","score":0.6904000043869019},{"id":"https://openalex.org/keywords/zipfs-law","display_name":"Zipf's law","score":0.6478000283241272},{"id":"https://openalex.org/keywords/coding","display_name":"Coding (social sciences)","score":0.636900007724762},{"id":"https://openalex.org/keywords/variable-length-code","display_name":"Variable-length code","score":0.6158000230789185},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.6108999848365784},{"id":"https://openalex.org/keywords/logarithm","display_name":"Logarithm","score":0.5286999940872192},{"id":"https://openalex.org/keywords/tunstall-coding","display_name":"Tunstall coding","score":0.5235000252723694},{"id":"https://openalex.org/keywords/information-theory","display_name":"Information theory","score":0.4869000017642975}],"concepts":[{"id":"https://openalex.org/C130811719","wikidata":"https://www.wikidata.org/wiki/Q2645","display_name":"Shannon\u2013Fano coding","level":4,"score":0.6904000043869019},{"id":"https://openalex.org/C125932096","wikidata":"https://www.wikidata.org/wiki/Q205472","display_name":"Zipf's law","level":2,"score":0.6478000283241272},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.636900007724762},{"id":"https://openalex.org/C60603091","wikidata":"https://www.wikidata.org/wiki/Q2981616","display_name":"Variable-length code","level":3,"score":0.6158000230789185},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.6108999848365784},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.559499979019165},{"id":"https://openalex.org/C39927690","wikidata":"https://www.wikidata.org/wiki/Q11197","display_name":"Logarithm","level":2,"score":0.5286999940872192},{"id":"https://openalex.org/C73231260","wikidata":"https://www.wikidata.org/wiki/Q7853376","display_name":"Tunstall coding","level":4,"score":0.5235000252723694},{"id":"https://openalex.org/C52622258","wikidata":"https://www.wikidata.org/wiki/Q131222","display_name":"Information theory","level":2,"score":0.4869000017642975},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.4521999955177307},{"id":"https://openalex.org/C1769480","wikidata":"https://www.wikidata.org/wiki/Q1345239","display_name":"Entropy encoding","level":3,"score":0.4334000051021576},{"id":"https://openalex.org/C46900642","wikidata":"https://www.wikidata.org/wiki/Q2647","display_name":"Huffman coding","level":3,"score":0.4262999892234802},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4108999967575073},{"id":"https://openalex.org/C9679016","wikidata":"https://www.wikidata.org/wiki/Q1417473","display_name":"Principle of maximum entropy","level":2,"score":0.4056999981403351},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3822999894618988},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.3483999967575073},{"id":"https://openalex.org/C3019641298","wikidata":"https://www.wikidata.org/wiki/Q625642","display_name":"Word length","level":2,"score":0.32199999690055847},{"id":"https://openalex.org/C135534801","wikidata":"https://www.wikidata.org/wiki/Q1128721","display_name":"Context-adaptive variable-length coding","level":4,"score":0.3192000091075897},{"id":"https://openalex.org/C153338461","wikidata":"https://www.wikidata.org/wiki/Q2651","display_name":"Arithmetic coding","level":4,"score":0.3188999891281128},{"id":"https://openalex.org/C190750250","wikidata":"https://www.wikidata.org/wiki/Q13533439","display_name":"Coding tree unit","level":3,"score":0.31790000200271606},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.2827000021934509},{"id":"https://openalex.org/C175732694","wikidata":"https://www.wikidata.org/wiki/Q1128713","display_name":"Context-adaptive binary arithmetic coding","level":3,"score":0.2644999921321869},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2563999891281128},{"id":"https://openalex.org/C101722063","wikidata":"https://www.wikidata.org/wiki/Q218825","display_name":"Random access","level":2,"score":0.25429999828338623},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.2531000077724457}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1080/09296174.2020.1778387","is_oa":false,"landing_page_url":"https://doi.org/10.1080/09296174.2020.1778387","pdf_url":null,"source":{"id":"https://openalex.org/S24321443","display_name":"Journal of Quantitative Linguistics","issn_l":"0929-6174","issn":["0929-6174","1744-5035"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319847","host_organization_name":"Routledge","host_organization_lineage":["https://openalex.org/P4310319847"],"host_organization_lineage_names":["Routledge"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Quantitative Linguistics","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:1906.01545","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1906.01545","pdf_url":"https://arxiv.org/pdf/1906.01545","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:upcommons.upc.edu:2117/333084","is_oa":true,"landing_page_url":"http://hdl.handle.net/2117/333084","pdf_url":null,"source":{"id":"https://openalex.org/S4210207057","display_name":"QRU Quaderns de Recerca en Urbanisme","issn_l":"2014-9689","issn":["2014-9689","2385-6777"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310322448","host_organization_name":"Q71272178","host_organization_lineage":["https://openalex.org/P4310322448"],"host_organization_lineage_names":["Q71272178"],"type":"journal"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1906.01545","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1906.01545","pdf_url":"https://arxiv.org/pdf/1906.01545","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4494121948","display_name":null,"funder_award_id":"TIN2017-89244-R","funder_id":"https://openalex.org/F4320326262","funder_display_name":"Ministerio de Asuntos Econ\u00f3micos y Transformaci\u00f3n Digital, Gobierno de Espa\u00f1a"},{"id":"https://openalex.org/G7397749619","display_name":null,"funder_award_id":"176305","funder_id":"https://openalex.org/F4320320924","funder_display_name":"Schweizerischer Nationalfonds zur F\u00f6rderung der Wissenschaftlichen Forschung"},{"id":"https://openalex.org/G8520527207","display_name":null,"funder_award_id":"FOR 2237","funder_id":"https://openalex.org/F4320320879","funder_display_name":"Deutsche Forschungsgemeinschaft"}],"funders":[{"id":"https://openalex.org/F4320320879","display_name":"Deutsche Forschungsgemeinschaft","ror":"https://ror.org/018mejw64"},{"id":"https://openalex.org/F4320320924","display_name":"Schweizerischer Nationalfonds zur F\u00f6rderung der Wissenschaftlichen Forschung","ror":"https://ror.org/00yjd3n13"},{"id":"https://openalex.org/F4320326262","display_name":"Ministerio de Asuntos Econ\u00f3micos y Transformaci\u00f3n Digital, Gobierno de Espa\u00f1a","ror":"https://ror.org/03sv46s19"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":47,"referenced_works":["https://openalex.org/W120098566","https://openalex.org/W595863337","https://openalex.org/W994102297","https://openalex.org/W1789494378","https://openalex.org/W1820435534","https://openalex.org/W1981346422","https://openalex.org/W1984940486","https://openalex.org/W1985650096","https://openalex.org/W1990598816","https://openalex.org/W1993803315","https://openalex.org/W1993984071","https://openalex.org/W2005222906","https://openalex.org/W2009643512","https://openalex.org/W2026522056","https://openalex.org/W2041432114","https://openalex.org/W2044340178","https://openalex.org/W2047402194","https://openalex.org/W2050249319","https://openalex.org/W2056007430","https://openalex.org/W2060479771","https://openalex.org/W2062750575","https://openalex.org/W2117688908","https://openalex.org/W2118004980","https://openalex.org/W2121300779","https://openalex.org/W2128777897","https://openalex.org/W2154612479","https://openalex.org/W2157261344","https://openalex.org/W2158923827","https://openalex.org/W2169476932","https://openalex.org/W2170521549","https://openalex.org/W2183162925","https://openalex.org/W2312217865","https://openalex.org/W2340632841","https://openalex.org/W2559566740","https://openalex.org/W2611598898","https://openalex.org/W2613002364","https://openalex.org/W2914154688","https://openalex.org/W2930291999","https://openalex.org/W2950627632","https://openalex.org/W2964954940","https://openalex.org/W2991181992","https://openalex.org/W3000218271","https://openalex.org/W3004556160","https://openalex.org/W3017131065","https://openalex.org/W4250348198","https://openalex.org/W4255110300","https://openalex.org/W4300289750"],"related_works":[],"abstract_inverted_index":{"The":[0],"problem":[1,22],"of":[2,9,23,40,90,99,110,173,179,183],"compression":[3],"in":[4,45,115,147,153],"standard":[5],"information":[6],"theory":[7,182],"consists":[8],"assigning":[10],"codes":[11,77],"as":[12,14,96,188,190],"short":[13],"possible":[15],"to":[16,52,59],"numbers.":[17],"Here":[18],"we":[19,169],"consider":[20],"the":[21,88,97,118,157,171,177],"optimal":[24,61,131,150,174],"coding":[25,30,62,85,114,133,151,175],"\u2013":[26,32],"under":[27,64],"an":[28,149],"arbitrary":[29],"scheme":[31,69],"and":[33],"show":[34],"that":[35,87,143,160],"it":[36,161],"predicts":[37,86,123],"Zipf\u2019s":[38,108,124],"law":[39,109],"abbreviation,":[41],"namely":[42],"a":[43,68,80,91,180],"tendency":[44],"natural":[46],"languages":[47],"for":[48,79,176],"more":[49,186],"frequent":[50],"words":[51],"be":[53],"shorter.":[54],"We":[55],"apply":[56],"this":[57],"result":[58],"investigate":[60],"also":[63,122],"so-called":[65],"non-singular":[66,84,113,132],"coding,":[67],"where":[70],"unique":[71],"segmentation":[72],"is":[73,104,146,162],"not":[74],"warranted":[75],"but":[76],"stand":[78],"distinct":[81],"number.":[82],"Optimal":[83,112],"length":[89],"word":[92],"should":[93],"grow":[94],"approximately":[95],"logarithm":[98],"its":[100],"frequency":[101],"rank,":[102],"which":[103],"again":[105],"consistent":[106],"with":[107,117,156],"abbreviation.":[111],"combination":[116],"maximum":[119],"entropy":[120],"principle":[121],"rank-frequency":[125],"distribution.":[126],"Furthermore,":[127],"our":[128],"findings":[129],"on":[130],"challenge":[134],"common":[135,158],"beliefs":[136],"about":[137],"random":[138,144],"typing.":[139],"It":[140],"turns":[141],"out":[142],"typing":[145],"fact":[148],"process,":[152],"stark":[154],"contrast":[155],"assumption":[159],"detached":[163],"from":[164],"cost":[165],"cutting":[166],"considerations.":[167],"Finally,":[168],"discuss":[170],"implications":[172],"construction":[178],"compact":[181],"Zipfian":[184],"laws":[185],"generally":[187],"well":[189],"other":[191],"linguistic":[192],"laws.":[193]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":50},{"year":2021,"cited_by_count":9},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":1}],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2019-06-14T00:00:00"}