{"id":"https://openalex.org/W4383889603","doi":"https://doi.org/10.53482/2023_54_407","title":"Direct and indirect evidence of compression of word lengths. Zipf\u2019s law of abbreviation revisited","display_name":"Direct and indirect evidence of compression of word lengths. Zipf\u2019s law of abbreviation revisited","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4383889603","doi":"https://doi.org/10.53482/2023_54_407"},"language":"en","primary_location":{"id":"doi:10.53482/2023_54_407","is_oa":true,"landing_page_url":"https://doi.org/10.53482/2023_54_407","pdf_url":"https://glottometrics.iqla.org/wp-content/uploads/2023/07/2023_54_407.pdf","source":{"id":"https://openalex.org/S4210217437","display_name":"Glottometrics","issn_l":"1617-8351","issn":["1617-8351","2625-8226"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Glottometrics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://glottometrics.iqla.org/wp-content/uploads/2023/07/2023_54_407.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5031781951","display_name":"Sonia Petrini","orcid":"https://orcid.org/0000-0002-0514-6223"},"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":"Sonia Petrini","raw_affiliation_strings":["Quantitative, Mathematical and Computational Linguistics Research Group. Departament de Ci\u00e8ncies de la Computaci\u00f3, Universitat Polit\u00e8cnica de Catalunya (UPC), Barcelona, Catalonia, Spain"],"raw_orcid":"https://orcid.org/0000-0002-0514-6223","affiliations":[{"raw_affiliation_string":"Quantitative, Mathematical and Computational Linguistics Research Group. Departament de Ci\u00e8ncies de la Computaci\u00f3, Universitat Polit\u00e8cnica de Catalunya (UPC), Barcelona, Catalonia, Spain","institution_ids":["https://openalex.org/I9617848"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048213747","display_name":"Antoni Casas-i-Mu\u00f1oz","orcid":"https://orcid.org/0000-0001-5690-316X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Antoni Casas-i-Mu\u00f1oz","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0001-5690-316X","affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003658281","display_name":"Jordi Cluet-i-Martinell","orcid":"https://orcid.org/0000-0003-4188-6728"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jordi Cluet-i-Martinell","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0003-4188-6728","affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001716357","display_name":"M WANG","orcid":"https://orcid.org/0000-0002-8262-9333"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mengxue Wang","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0002-8262-9333","affiliations":[]},{"author_position":"middle","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"]},{"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":["DE","ES"],"is_corresponding":false,"raw_author_name":"Christian Bentz","raw_affiliation_strings":["Department of Linguistics, University of T\u00fcbingen, T\u00fcbingen, Germany","Universitat Polit\u00e8cnica de Catalunya (UPC), Barcelona School of Informatics, Barcelona, Catalonia, Spain"],"raw_orcid":"https://orcid.org/0000-0001-6570-9326","affiliations":[{"raw_affiliation_string":"Department of Linguistics, University of T\u00fcbingen, T\u00fcbingen, Germany","institution_ids":["https://openalex.org/I8087733"]},{"raw_affiliation_string":"Universitat Polit\u00e8cnica de Catalunya (UPC), Barcelona School of Informatics, Barcelona, Catalonia, Spain","institution_ids":["https://openalex.org/I9617848"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5014322193","display_name":"Ramon Ferrer\u2010i\u2010Cancho","orcid":"https://orcid.org/0000-0002-7820-923X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ramon Ferrer-i-Cancho","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0002-7820-923X","affiliations":[]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.3147,"has_fulltext":true,"cited_by_count":10,"citation_normalized_percentile":{"value":0.83693041,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"54","issue":null,"first_page":"58","last_page":"87"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12380","display_name":"Authorship Attribution and Profiling","score":0.9909999966621399,"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":0.9909999966621399,"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":0.9386000037193298,"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/T13326","display_name":"Biochemical and Structural Characterization","score":0.9196000099182129,"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/zipfs-law","display_name":"Zipf's law","score":0.9077783823013306},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.6136942505836487},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.49478334188461304},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.48268675804138184},{"id":"https://openalex.org/keywords/argument","display_name":"Argument (complex analysis)","score":0.4585869014263153},{"id":"https://openalex.org/keywords/word-length","display_name":"Word length","score":0.42553389072418213},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.33450624346733093},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.2625996768474579},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.2346487045288086},{"id":"https://openalex.org/keywords/philosophy","display_name":"Philosophy","score":0.08550715446472168}],"concepts":[{"id":"https://openalex.org/C125932096","wikidata":"https://www.wikidata.org/wiki/Q205472","display_name":"Zipf's law","level":2,"score":0.9077783823013306},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.6136942505836487},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.49478334188461304},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.48268675804138184},{"id":"https://openalex.org/C98184364","wikidata":"https://www.wikidata.org/wiki/Q1780131","display_name":"Argument (complex analysis)","level":2,"score":0.4585869014263153},{"id":"https://openalex.org/C3019641298","wikidata":"https://www.wikidata.org/wiki/Q625642","display_name":"Word length","level":2,"score":0.42553389072418213},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.33450624346733093},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2625996768474579},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.2346487045288086},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.08550715446472168},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.53482/2023_54_407","is_oa":true,"landing_page_url":"https://doi.org/10.53482/2023_54_407","pdf_url":"https://glottometrics.iqla.org/wp-content/uploads/2023/07/2023_54_407.pdf","source":{"id":"https://openalex.org/S4210217437","display_name":"Glottometrics","issn_l":"1617-8351","issn":["1617-8351","2625-8226"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Glottometrics","raw_type":"journal-article"},{"id":"pmh:oai:upcommons.upc.edu:2117/394676","is_oa":true,"landing_page_url":"https://hdl.handle.net/2117/394676","pdf_url":"https://upcommons.upc.edu/bitstreams/5cdf86ce-4adf-40e8-8719-3fa6cec3d47c/download","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-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"}],"best_oa_location":{"id":"doi:10.53482/2023_54_407","is_oa":true,"landing_page_url":"https://doi.org/10.53482/2023_54_407","pdf_url":"https://glottometrics.iqla.org/wp-content/uploads/2023/07/2023_54_407.pdf","source":{"id":"https://openalex.org/S4210217437","display_name":"Glottometrics","issn_l":"1617-8351","issn":["1617-8351","2625-8226"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Glottometrics","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.49000000953674316,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320328447","display_name":"Universitat Polit\u00e8cnica de Catalunya","ror":"https://ror.org/03mb6wj31"}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4383889603.pdf"},"referenced_works_count":26,"referenced_works":["https://openalex.org/W103650626","https://openalex.org/W1524562168","https://openalex.org/W1977597971","https://openalex.org/W2000196122","https://openalex.org/W2003342198","https://openalex.org/W2022564164","https://openalex.org/W2144186594","https://openalex.org/W2192963863","https://openalex.org/W2288336636","https://openalex.org/W2478708596","https://openalex.org/W2604591444","https://openalex.org/W2797646548","https://openalex.org/W2969233311","https://openalex.org/W2991168776","https://openalex.org/W2993383518","https://openalex.org/W3098104893","https://openalex.org/W3101776888","https://openalex.org/W3163058944","https://openalex.org/W3169532011","https://openalex.org/W3202156680","https://openalex.org/W3216986193","https://openalex.org/W4220995813","https://openalex.org/W4281764986","https://openalex.org/W4288070136","https://openalex.org/W6648982606","https://openalex.org/W6696447242"],"related_works":["https://openalex.org/W2041504988","https://openalex.org/W2040288513","https://openalex.org/W2808014614","https://openalex.org/W2068578356","https://openalex.org/W39918333","https://openalex.org/W2075174955","https://openalex.org/W237537940","https://openalex.org/W1898422521","https://openalex.org/W2133478886","https://openalex.org/W4235762796"],"abstract_inverted_index":{"Zipf\u2019s":[0,54],"law":[1,58,93,103,127,143],"of":[2,6,15,39,49,65,69,74,81,88,94,128,133,135,144,149,156,159,186,189,209,211],"abbreviation,":[3],"the":[4,16,25,30,47,72,79,86,92,102,126,138,142,154,187,201,207],"tendency":[5],"more":[7],"frequent":[8],"words":[9],"to":[10,46,77,203],"be":[11],"shorter,":[12],"is":[13,42,111,146],"one":[14],"most":[17],"solid":[18],"candidates":[19],"for":[20,32,166],"a":[21,37,63,66,147,163,167],"linguistic":[22,122,179],"universal,":[23],"in":[24,106,113,115,117,192,196,214],"sense":[26],"that":[27,41,101,141,171],"it":[28],"has":[29,59],"potential":[31],"being":[33],"exceptionless":[34],"or":[35,194],"with":[36,91,125],"number":[38,48],"exceptions":[40],"vanishingly":[43],"small":[44],"compared":[45],"languages":[50,119,136],"on":[51],"Earth.":[52],"Since":[53],"pioneering":[55],"research,":[56],"this":[57],"been":[60],"viewed":[61],"as":[62],"manifestation":[64],"universal":[67],"principle":[68],"communication,":[70],"i.e.":[71],"minimization":[73],"word":[75,109,172,212],"lengths,":[76],"reduce":[78],"effort":[80],"communication.":[82],"Here":[83],"we":[84,97,161],"revisit":[85],"concordance":[87],"written":[89],"language":[90],"abbreviation.":[95],"Crucially,":[96],"provide":[98],"wider":[99],"evidence":[100,132,158],"holds":[104],"also":[105],"speech":[107],"(when":[108],"length":[110],"measured":[112],"time),":[114],"particular":[116],"46":[118],"from":[120],"14":[121],"families.":[123],"Agreement":[124],"abbreviation":[129,145],"provides":[130],"indirect":[131],"compression":[134],"via":[137],"theoretical":[139],"argument":[140],"prediction":[148],"optimal":[150],"coding.":[151],"Motivated":[152],"by":[153],"need":[155],"direct":[157],"compression,":[160],"derive":[162],"simple":[164],"formula":[165],"random":[168],"baseline":[169],"indicating":[170],"lengths":[173,213],"are":[174],"systematically":[175],"below":[176],"chance,":[177],"across":[178],"families":[180],"and":[181,184,205],"writing":[182],"systems,":[183],"independently":[185],"unit":[188],"measurement":[190],"(length":[191],"characters":[193],"duration":[195],"time).":[197],"Our":[198],"work":[199],"paves":[200],"way":[202],"measure":[204],"compare":[206],"degree":[208],"optimality":[210],"languages.":[215]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2}],"updated_date":"2026-07-26T07:53:14.480251","created_date":"2023-07-12T00:00:00"}
