{"id":"https://openalex.org/W4384643698","doi":"https://doi.org/10.1145/3539618.3591942","title":"A Unified Formulation for the Frequency Distribution of Word Frequencies using the Inverse Zipf's Law","display_name":"A Unified Formulation for the Frequency Distribution of Word Frequencies using the Inverse Zipf's Law","publication_year":2023,"publication_date":"2023-07-18","ids":{"openalex":"https://openalex.org/W4384643698","doi":"https://doi.org/10.1145/3539618.3591942"},"language":"en","primary_location":{"id":"doi:10.1145/3539618.3591942","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3539618.3591942","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 46th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5001281785","display_name":"Can \u00d6zbey","orcid":"https://orcid.org/0009-0005-8432-9413"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Can \u00d6zbey","raw_affiliation_strings":["Huawei Turkey R&D Center, Istanbul, Turkey"],"raw_orcid":"https://orcid.org/0009-0005-8432-9413","affiliations":[{"raw_affiliation_string":"Huawei Turkey R&D Center, Istanbul, Turkey","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069570906","display_name":"Talha \u00c7olako\u011flu","orcid":"https://orcid.org/0000-0002-4524-862X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Talha \u00c7olako\u011flu","raw_affiliation_strings":["Huawei Turkey R&D Center, Istanbul, Turkey"],"raw_orcid":"https://orcid.org/0000-0002-4524-862X","affiliations":[{"raw_affiliation_string":"Huawei Turkey R&D Center, Istanbul, Turkey","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044289159","display_name":"M\u00fccahit Bilici","orcid":"https://orcid.org/0009-0005-4456-5163"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"M. \u015eafak Bilici","raw_affiliation_strings":["Huawei Turkey R&D Center, Istanbul, Turkey"],"raw_orcid":"https://orcid.org/0009-0005-4456-5163","affiliations":[{"raw_affiliation_string":"Huawei Turkey R&D Center, Istanbul, Turkey","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5012997064","display_name":"Ekin Can Erku\u015f","orcid":"https://orcid.org/0000-0002-2445-5929"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ekin Can Erku\u015f;","raw_affiliation_strings":["Huawei Turkey R&D Center, Istanbul, Turkey"],"raw_orcid":"https://orcid.org/0000-0002-2445-5929","affiliations":[{"raw_affiliation_string":"Huawei Turkey R&D Center, Istanbul, Turkey","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5001281785"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.08510742,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1776","last_page":"1780"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12592","display_name":"Opinion Dynamics and Social Influence","score":0.9883000254631042,"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"}},"topics":[{"id":"https://openalex.org/T12592","display_name":"Opinion Dynamics and Social Influence","score":0.9883000254631042,"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/T12380","display_name":"Authorship Attribution and Profiling","score":0.9846000075340271,"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/T10064","display_name":"Complex Network Analysis Techniques","score":0.9757999777793884,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/zipfs-law","display_name":"Zipf's law","score":0.9487611055374146},{"id":"https://openalex.org/keywords/word-lists-by-frequency","display_name":"Word lists by frequency","score":0.5493025183677673},{"id":"https://openalex.org/keywords/inverse","display_name":"Inverse","score":0.47999948263168335},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.46500998735427856},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.4570394456386566},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.4318722188472748},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4214223027229309},{"id":"https://openalex.org/keywords/power-law","display_name":"Power law","score":0.4179448187351227},{"id":"https://openalex.org/keywords/principle-of-maximum-entropy","display_name":"Principle of maximum entropy","score":0.4106401801109314},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3816666603088379},{"id":"https://openalex.org/keywords/applied-mathematics","display_name":"Applied mathematics","score":0.3645983934402466},{"id":"https://openalex.org/keywords/statistical-physics","display_name":"Statistical physics","score":0.36074239015579224},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.28539222478866577},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.267983615398407}],"concepts":[{"id":"https://openalex.org/C125932096","wikidata":"https://www.wikidata.org/wiki/Q205472","display_name":"Zipf's law","level":2,"score":0.9487611055374146},{"id":"https://openalex.org/C175293574","wikidata":"https://www.wikidata.org/wiki/Q697133","display_name":"Word lists by frequency","level":3,"score":0.5493025183677673},{"id":"https://openalex.org/C207467116","wikidata":"https://www.wikidata.org/wiki/Q4385666","display_name":"Inverse","level":2,"score":0.47999948263168335},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.46500998735427856},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.4570394456386566},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.4318722188472748},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4214223027229309},{"id":"https://openalex.org/C87040749","wikidata":"https://www.wikidata.org/wiki/Q428971","display_name":"Power law","level":2,"score":0.4179448187351227},{"id":"https://openalex.org/C9679016","wikidata":"https://www.wikidata.org/wiki/Q1417473","display_name":"Principle of maximum entropy","level":2,"score":0.4106401801109314},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3816666603088379},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.3645983934402466},{"id":"https://openalex.org/C121864883","wikidata":"https://www.wikidata.org/wiki/Q677916","display_name":"Statistical physics","level":1,"score":0.36074239015579224},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.28539222478866577},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.267983615398407},{"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3539618.3591942","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3539618.3591942","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 46th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6100000143051147,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W1480278483","https://openalex.org/W1517590677","https://openalex.org/W1580638181","https://openalex.org/W1967712865","https://openalex.org/W1973839243","https://openalex.org/W1994463867","https://openalex.org/W2002869374","https://openalex.org/W2007915090","https://openalex.org/W2014143342","https://openalex.org/W2022812583","https://openalex.org/W2025456003","https://openalex.org/W2041532239","https://openalex.org/W2044133458","https://openalex.org/W2050963206","https://openalex.org/W2053134999","https://openalex.org/W2073762854","https://openalex.org/W2079656678","https://openalex.org/W2094692697","https://openalex.org/W2113514430","https://openalex.org/W2127667244","https://openalex.org/W2183162925","https://openalex.org/W2620833468","https://openalex.org/W2741366111","https://openalex.org/W2966549749","https://openalex.org/W3040875233","https://openalex.org/W3124136095","https://openalex.org/W3125969228","https://openalex.org/W3183153947","https://openalex.org/W4301031423","https://openalex.org/W6732108346"],"related_works":["https://openalex.org/W2075174955","https://openalex.org/W39918333","https://openalex.org/W2007915090","https://openalex.org/W2023581076","https://openalex.org/W2098897829","https://openalex.org/W2411421322","https://openalex.org/W3032248989","https://openalex.org/W2041504988","https://openalex.org/W2060836063","https://openalex.org/W3098710055"],"abstract_inverted_index":{"The":[0],"power-law":[1],"approximation":[2],"for":[3,16,99,119],"the":[4,24,34,37,51,54,68,78,85,104,134,137],"frequency":[5],"distribution":[6,57],"of":[7,36,39,53,61,81,103,111,123,128,136],"words":[8],"postulated":[9],"by":[10],"Zipf":[11],"has":[12,30],"been":[13,31],"extensively":[14],"studied":[15],"decades,":[17],"which":[18],"led":[19],"to":[20,33,76,132],"many":[21],"variations":[22],"on":[23,84,95],"theme.":[25],"However,":[26],"comparatively":[27],"less":[28],"attention":[29],"paid":[32],"investigation":[35],"case":[38],"word":[40,63],"frequencies.":[41],"In":[42],"this":[43],"paper,":[44],"we":[45],"derive":[46],"its":[47],"analytical":[48],"expression":[49],"from":[50],"inverse":[52],"underlying":[55],"rank-size":[56],"as":[58],"a":[59,73,100,108,120],"function":[60],"total":[62],"count,":[64],"vocabulary":[65],"size":[66],"and":[67],"shape":[69,105],"parameter,":[70],"thereby":[71],"providing":[72],"unified":[74],"framework":[75],"explain":[77],"nonlinear":[79],"behavior":[80],"low":[82],"frequencies":[83],"log-log":[86],"scale.":[87],"We":[88],"also":[89],"present":[90],"an":[91],"efficient":[92],"method":[93],"based":[94],"relative":[96],"entropy":[97],"minimization":[98],"robust":[101],"estimation":[102],"parameter":[106],"using":[107],"small":[109],"number":[110],"empirical":[112],"low-frequency":[113],"probabilities.":[114],"Experiments":[115],"were":[116],"carried":[117],"out":[118],"selected":[121],"set":[122],"languages":[124],"with":[125],"varying":[126],"degrees":[127],"inflection":[129],"in":[130],"order":[131],"demonstrate":[133],"effectiveness":[135],"proposed":[138],"approach.":[139]},"counts_by_year":[],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}