{"id":"https://openalex.org/W4285100863","doi":"https://doi.org/10.1109/comm54429.2022.9817208","title":"Revisiting the idea of a representative linguistic corpus","display_name":"Revisiting the idea of a representative linguistic corpus","publication_year":2022,"publication_date":"2022-06-16","ids":{"openalex":"https://openalex.org/W4285100863","doi":"https://doi.org/10.1109/comm54429.2022.9817208"},"language":"en","primary_location":{"id":"doi:10.1109/comm54429.2022.9817208","is_oa":false,"landing_page_url":"https://doi.org/10.1109/comm54429.2022.9817208","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 14th International Conference on Communications (COMM)","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/A5078520582","display_name":"Alexandru Dinu","orcid":"https://orcid.org/0009-0005-4330-3145"},"institutions":[{"id":"https://openalex.org/I61641377","display_name":"Universitatea Na\u021bional\u0103 de \u0218tiin\u021b\u0103 \u0219i Tehnologie Politehnica Bucure\u0219ti","ror":"https://ror.org/0558j5q12","country_code":"RO","type":"education","lineage":["https://openalex.org/I61641377"]}],"countries":["RO"],"is_corresponding":true,"raw_author_name":"Alexandru Dinu","raw_affiliation_strings":["POLITEHNICA University of Bucharest,Faculty of Electronics, Telecommunications and Information Technology,Romania","Faculty of Electronics, Telecommunications and Information Technology, POLITEHNICA University of Bucharest, Romania"],"affiliations":[{"raw_affiliation_string":"POLITEHNICA University of Bucharest,Faculty of Electronics, Telecommunications and Information Technology,Romania","institution_ids":["https://openalex.org/I61641377"]},{"raw_affiliation_string":"Faculty of Electronics, Telecommunications and Information Technology, POLITEHNICA University of Bucharest, Romania","institution_ids":["https://openalex.org/I61641377"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5049776987","display_name":"Adriana Vlad","orcid":null},"institutions":[{"id":"https://openalex.org/I58077936","display_name":"Romanian Academy","ror":"https://ror.org/0561n6946","country_code":"RO","type":"archive","lineage":["https://openalex.org/I58077936"]},{"id":"https://openalex.org/I33800924","display_name":"Academy of Romanian Scientists","ror":"https://ror.org/04ybnj478","country_code":"RO","type":"facility","lineage":["https://openalex.org/I33800924"]}],"countries":["RO"],"is_corresponding":false,"raw_author_name":"Adriana Vlad","raw_affiliation_strings":["The Research Institute for Artificial Intelligence, Romanian Academy,Bucharest,Romania","The Research Institute for Artificial Intelligence, Romanian Academy, Bucharest, Romania"],"affiliations":[{"raw_affiliation_string":"The Research Institute for Artificial Intelligence, Romanian Academy,Bucharest,Romania","institution_ids":["https://openalex.org/I58077936","https://openalex.org/I33800924"]},{"raw_affiliation_string":"The Research Institute for Artificial Intelligence, Romanian Academy, Bucharest, Romania","institution_ids":["https://openalex.org/I58077936"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5078520582"],"corresponding_institution_ids":["https://openalex.org/I61641377"],"apc_list":null,"apc_paid":null,"fwci":0.1326,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.51369957,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"5","issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9954000115394592,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9954000115394592,"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/T12380","display_name":"Authorship Attribution and Profiling","score":0.9621000289916992,"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/representativeness-heuristic","display_name":"Representativeness heuristic","score":0.858195960521698},{"id":"https://openalex.org/keywords/zipfs-law","display_name":"Zipf's law","score":0.802203357219696},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.6742069721221924},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6399799585342407},{"id":"https://openalex.org/keywords/independence","display_name":"Independence (probability theory)","score":0.6251705884933472},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5658941268920898},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.564639151096344},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.545218288898468},{"id":"https://openalex.org/keywords/corpus-linguistics","display_name":"Corpus linguistics","score":0.5225214958190918},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46777239441871643},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.4175495505332947},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.28303825855255127},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2560059428215027}],"concepts":[{"id":"https://openalex.org/C37381756","wikidata":"https://www.wikidata.org/wiki/Q20203288","display_name":"Representativeness heuristic","level":2,"score":0.858195960521698},{"id":"https://openalex.org/C125932096","wikidata":"https://www.wikidata.org/wiki/Q205472","display_name":"Zipf's law","level":2,"score":0.802203357219696},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.6742069721221924},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6399799585342407},{"id":"https://openalex.org/C35651441","wikidata":"https://www.wikidata.org/wiki/Q625303","display_name":"Independence (probability theory)","level":2,"score":0.6251705884933472},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5658941268920898},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.564639151096344},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.545218288898468},{"id":"https://openalex.org/C532629269","wikidata":"https://www.wikidata.org/wiki/Q865083","display_name":"Corpus linguistics","level":2,"score":0.5225214958190918},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46777239441871643},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.4175495505332947},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.28303825855255127},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2560059428215027},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/comm54429.2022.9817208","is_oa":false,"landing_page_url":"https://doi.org/10.1109/comm54429.2022.9817208","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 14th International Conference on Communications (COMM)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.8199999928474426}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W25698700","https://openalex.org/W2037347296","https://openalex.org/W2137091081","https://openalex.org/W2886473070","https://openalex.org/W3042873966","https://openalex.org/W3209289172","https://openalex.org/W4229842515","https://openalex.org/W6601076160"],"related_works":["https://openalex.org/W3159631231","https://openalex.org/W3123832408","https://openalex.org/W2137719806","https://openalex.org/W4306248409","https://openalex.org/W2744330362","https://openalex.org/W4211213551","https://openalex.org/W2332151799","https://openalex.org/W2096748633","https://openalex.org/W4225941136","https://openalex.org/W193977043"],"abstract_inverted_index":{"The":[0,18,109],"paper":[1],"revisits":[2],"the":[3,36,39,45,54,62,69,86,102,118,131,141,162],"notion":[4],"of":[5,7,15,38,49,64,78,88,143,164,166],"representativeness":[6,165],"a":[8,136,167],"linguistic":[9,168],"corpus":[10,47,120],"obtained":[11,112],"through":[12],"successive":[13],"concatenations":[14],"author":[16,32,153],"corpora.":[17],"means":[19],"for":[20,52,58],"investigating":[21],"this":[22,59,107],"concept":[23],"is":[24],"statistical":[25,65,90],"probability":[26,66],"estimation":[27,67],"by":[28],"piecing":[29],"together":[30],"multiple":[31],"corpora":[33,154],"and":[34,68,81,97,128,149],"evaluating":[35],"consistency":[37],"resulted":[40],"construction":[41],"in":[42,106,123],"comparison":[43],"with":[44,85,101,140,161],"overall":[46],"consisting":[48],"full":[50],"texts":[51],"all":[53],"authors":[55],"considered.":[56],"Essential":[57],"investigation":[60],"are":[61],"concepts":[63],"associated":[70],"confidence":[71],"intervals.":[72],"Furthermore,":[73],"we":[74,82],"also":[75],"made":[76,83],"use":[77],"previous":[79],"results":[80,111,157],"correlations":[84],"notions":[87],"minimum":[89],"independence":[91],"distance,":[92],"Zipf's":[93],"Law":[94],"priority":[95],"areas":[96],"common":[98,150],"words,":[99],"starting":[100],"new":[103],"methodology":[104],"proposed":[105],"paper.":[108],"experimental":[110],"shows":[113],"that":[114],"when":[115],"data":[116],"from":[117],"analyzed":[119,132],"were":[121],"collected":[122],"an":[124],"i.i.d.":[125],"manner":[126],"(independent":[127],"identically":[129],"distributed),":[130],"word":[133],"sets":[134],"had":[135],"very":[137],"good":[138],"overlap":[139],"set":[142],"Zipf":[144],"Area":[145],"1":[146],"words":[147,151],"(99%)":[148],"among":[152],"(75%).":[155],"These":[156],"can":[158],"be":[159],"aligned":[160],"idea":[163],"corpus.":[169]},"counts_by_year":[{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}