{"id":"https://openalex.org/W2963931980","doi":null,"title":"Entropy of a Zipfian Distributed Lexicon","display_name":"Entropy of a Zipfian Distributed Lexicon","publication_year":2013,"publication_date":"2013-01-01","ids":{"openalex":"https://openalex.org/W2963931980","mag":"2963931980"},"language":"en","primary_location":{"id":"mag:1716791217","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/pdf/1307.0898.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"arXiv (Cornell University)","raw_type":null},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://arxiv.org/pdf/1307.0898.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5035820144","display_name":"Leonardo Carneiro Araujo","orcid":"https://orcid.org/0000-0003-3884-2177","observed_orcids":["https://orcid.org/0000-0003-3884-2177"]},"institutions":[{"id":"https://openalex.org/I166595947","display_name":"Federal University of S\u00e3o Jo\u00e3o del-Rei","ror":"https://ror.org/03vrj4p82","country_code":"BR","type":"education","lineage":["https://openalex.org/I166595947"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Leonardo Carneiro de Ara\u00fajo","raw_affiliation_strings":["Federal University of Sao Joao del-Rei"],"raw_orcid":"https://orcid.org/0000-0003-3884-2177","affiliations":[{"raw_affiliation_string":"Federal University of Sao Joao del-Rei","institution_ids":["https://openalex.org/I166595947"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047796796","display_name":"Tha\u00efs Crist\u00f3faro Silva","orcid":"https://orcid.org/0000-0002-9187-4154","observed_orcids":["https://orcid.org/0000-0002-9187-4154","https://orcid.org/0000-0003-0386-6304"]},"institutions":[{"id":"https://openalex.org/I110200422","display_name":"Universidade Federal de Minas Gerais","ror":"https://ror.org/0176yjw32","country_code":"BR","type":"education","lineage":["https://openalex.org/I110200422"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Tha\u00efs Crist\u00f3faro-Silva","raw_affiliation_strings":["FEDERAL UNIVERSITY OF MINAS GERAIS"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"FEDERAL UNIVERSITY OF MINAS GERAIS","institution_ids":["https://openalex.org/I110200422"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5052503768","display_name":"Hani Camille Yehia","orcid":"https://orcid.org/0000-0003-4578-0525","observed_orcids":["https://orcid.org/0000-0003-4578-0525"]},"institutions":[{"id":"https://openalex.org/I110200422","display_name":"Universidade Federal de Minas Gerais","ror":"https://ror.org/0176yjw32","country_code":"BR","type":"education","lineage":["https://openalex.org/I110200422"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Hani Camille Yehia","raw_affiliation_strings":["FEDERAL UNIVERSITY OF MINAS GERAIS"],"raw_orcid":"https://orcid.org/0000-0003-4578-0525","affiliations":[{"raw_affiliation_string":"FEDERAL UNIVERSITY OF MINAS GERAIS","institution_ids":["https://openalex.org/I110200422"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"26","issue":null,"first_page":"38","last_page":"49"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.3869999945163727,"subfield":{"id":"https://openalex.org/subfields/2614","display_name":"Theoretical Computer Science"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.3869999945163727,"subfield":{"id":"https://openalex.org/subfields/2614","display_name":"Theoretical Computer Science"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12261","display_name":"Statistical Mechanics and Entropy","score":0.21660000085830688,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.12999999523162842,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/zipf-s-law","display_name":"Zipf's law","score":0.8420000076293945},{"id":"https://openalex.org/keywords/entropy-maximization","display_name":"entropy maximization","score":0.6309999823570251},{"id":"https://openalex.org/keywords/communication-effort","display_name":"communication effort","score":0.4620000123977661},{"id":"https://openalex.org/keywords/linguistic-statistics","display_name":"language statistics","score":0.36500000953674316},{"id":"https://openalex.org/keywords/natural-language","display_name":"natural language","score":0.3190000057220459},{"id":"https://openalex.org/keywords/entropy-estimation","display_name":"entropy estimation","score":0.5149999856948853},{"id":"https://openalex.org/keywords/word-frequency-distribution","display_name":"word frequency distribution","score":0.5479999780654907}],"concepts":[{"id":"https://openalex.org/C125932096","wikidata":"https://www.wikidata.org/wiki/Q205472","display_name":"Zipf's law","level":2,"score":0.861626148223877},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.689077615737915},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6613030433654785},{"id":"https://openalex.org/C2778121359","wikidata":"https://www.wikidata.org/wiki/Q8096","display_name":"Lexicon","level":2,"score":0.5524979829788208},{"id":"https://openalex.org/C32848918","wikidata":"https://www.wikidata.org/wiki/Q845789","display_name":"Observable","level":2,"score":0.4953440725803375},{"id":"https://openalex.org/C2780388253","wikidata":"https://www.wikidata.org/wiki/Q5421508","display_name":"Exponent","level":2,"score":0.4615490734577179},{"id":"https://openalex.org/C149441793","wikidata":"https://www.wikidata.org/wiki/Q200726","display_name":"Probability distribution","level":2,"score":0.42365384101867676},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3512852191925049},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3209000825881958},{"id":"https://openalex.org/C121864883","wikidata":"https://www.wikidata.org/wiki/Q677916","display_name":"Statistical physics","level":1,"score":0.3203495740890503},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2901112139225006},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.22968602180480957},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0810118019580841},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"mag:1716791217","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/pdf/1307.0898.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"arXiv (Cornell University)","raw_type":null},{"id":"mag:2963931980","doi":null,"is_oa":false,"landing_page_url":"https://dblp.uni-trier.de/db/journals/glottometrics/glottometrics26.html#AraujoSY13","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":"Glottometrics","raw_type":null}],"best_oa_location":{"id":"mag:1716791217","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/pdf/1307.0898.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"arXiv (Cornell University)","raw_type":null},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W1591095982","https://openalex.org/W1976724989","https://openalex.org/W1980509985","https://openalex.org/W1995875735","https://openalex.org/W2009047999","https://openalex.org/W2028769319","https://openalex.org/W2040712685","https://openalex.org/W2079145130","https://openalex.org/W2083590325","https://openalex.org/W2097337361","https://openalex.org/W2116978935","https://openalex.org/W2120824791","https://openalex.org/W2158195707","https://openalex.org/W2170521549","https://openalex.org/W2312217865","https://openalex.org/W2321470647"],"related_works":["https://openalex.org/W2054612702","https://openalex.org/W4289541476","https://openalex.org/W1939081331","https://openalex.org/W2105736348","https://openalex.org/W7095911552","https://openalex.org/W7028921344","https://openalex.org/W7098903539","https://openalex.org/W2003342198","https://openalex.org/W2009643512","https://openalex.org/W6944502849"],"abstract_inverted_index":{"This":[0,32,51],"article":[1],"presents":[2],"the":[3,6,39,43,65,68,75,78,81,88,94,97,115,119,128],"calculation":[4],"of":[5,8,45,80,96,114,122,130],"entropy":[7,36,79,110,120],"a":[9,17,46],"system":[10,19],"with":[11,56,64,118],"Zipfian":[12],"distribution.":[13],"It":[14],"shows":[15],"that":[16],"communication":[18,72],"tends":[20],"to":[21,87,107],"present":[22],"an":[23],"exponent":[24,89],"value":[25,90],"close":[26],"to,":[27],"but":[28],"greater":[29],"than":[30],"one.":[31],"choice":[33],"both":[34],"maximizes":[35],"and,":[37],"at":[38],"same":[40],"time,":[41],"enables":[42],"retention":[44],"feasible":[47],"and":[48,63,70,133,138],"growing":[49],"lexicon.":[50],"result":[52],"is":[53,58,84],"in":[54,60,127],"accordance":[55],"what":[57],"observed":[59],"natural":[61],"languages":[62],"balance":[66],"between":[67],"speaker":[69],"listener":[71],"efforts.":[73],"On":[74],"other":[76],"hand,":[77],"communicating":[82],"source":[83],"very":[85,108],"sensitive":[86],"as":[91,93],"well":[92],"length":[95],"observable":[98],"data.":[99],"Slight":[100],"deviations":[101],"on":[102],"these":[103],"parameters":[104],"might":[105],"lead":[106],"different":[109],"measurements.":[111],"A":[112],"comparison":[113],"estimation":[116],"proposed":[117],"measure":[121],"written":[123],"texts":[124],"yields":[125],"errors":[126],"order":[129],"0.3":[131],"bits":[132,135],"0.05":[134],"for":[136],"non-smoothed":[137],"smoothed":[139],"distributions,":[140],"respectively.":[141]},"counts_by_year":[],"updated_date":"2026-10-13T10:08:12.033832","created_date":"2019-07-30T00:00:00"}