{"id":"https://openalex.org/W2107251449","doi":"https://doi.org/10.1017/s1351324910000161","title":"The automatic identification of lexical variation between language varieties","display_name":"The automatic identification of lexical variation between language varieties","publication_year":2010,"publication_date":"2010-10-01","ids":{"openalex":"https://openalex.org/W2107251449","doi":"https://doi.org/10.1017/s1351324910000161","mag":"2107251449"},"language":"en","primary_location":{"id":"doi:10.1017/s1351324910000161","is_oa":false,"landing_page_url":"https://doi.org/10.1017/s1351324910000161","pdf_url":null,"source":{"id":"https://openalex.org/S18088403","display_name":"Natural Language Engineering","issn_l":"1351-3249","issn":["1351-3249","1469-8110"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311721","host_organization_name":"Cambridge University Press","host_organization_lineage":["https://openalex.org/P4310311721","https://openalex.org/P4310311702"],"host_organization_lineage_names":["Cambridge University Press","University of Cambridge"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Natural Language Engineering","raw_type":"journal-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/A5057289584","display_name":"Yves Peirsman","orcid":null},"institutions":[{"id":"https://openalex.org/I2802067006","display_name":"Research Foundation - Flanders","ror":"https://ror.org/03qtxy027","country_code":"BE","type":"government","lineage":["https://openalex.org/I2802067006"]},{"id":"https://openalex.org/I99464096","display_name":"KU Leuven","ror":"https://ror.org/05f950310","country_code":"BE","type":"education","lineage":["https://openalex.org/I99464096"]}],"countries":["BE"],"is_corresponding":true,"raw_author_name":"YVES PEIRSMAN","raw_affiliation_strings":["Quantitative Lexicology and Variational Linguistics (QLVL), University of Leuven, Blijde-Inkomststraat 21 P.O. Box 3308, 3000 Leuven, Belgium","Research Foundation \u2013 Flanders (FWO), Egmontstraat 5, 1000 Brussels, Belgium"],"affiliations":[{"raw_affiliation_string":"Quantitative Lexicology and Variational Linguistics (QLVL), University of Leuven, Blijde-Inkomststraat 21 P.O. Box 3308, 3000 Leuven, Belgium","institution_ids":["https://openalex.org/I99464096"]},{"raw_affiliation_string":"Research Foundation \u2013 Flanders (FWO), Egmontstraat 5, 1000 Brussels, Belgium","institution_ids":["https://openalex.org/I2802067006"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066176620","display_name":"Dirk Geeraerts","orcid":"https://orcid.org/0000-0001-6350-0588"},"institutions":[{"id":"https://openalex.org/I99464096","display_name":"KU Leuven","ror":"https://ror.org/05f950310","country_code":"BE","type":"education","lineage":["https://openalex.org/I99464096"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"DIRK GEERAERTS","raw_affiliation_strings":["Quantitative Lexicology and Variational Linguistics (QLVL), University of Leuven, Blijde-Inkomststraat 21 P.O. Box 3308, 3000 Leuven, Belgium"],"affiliations":[{"raw_affiliation_string":"Quantitative Lexicology and Variational Linguistics (QLVL), University of Leuven, Blijde-Inkomststraat 21 P.O. Box 3308, 3000 Leuven, Belgium","institution_ids":["https://openalex.org/I99464096"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5048483716","display_name":"Dirk Speelman","orcid":"https://orcid.org/0000-0003-1561-1851"},"institutions":[{"id":"https://openalex.org/I99464096","display_name":"KU Leuven","ror":"https://ror.org/05f950310","country_code":"BE","type":"education","lineage":["https://openalex.org/I99464096"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"DIRK SPEELMAN","raw_affiliation_strings":["Quantitative Lexicology and Variational Linguistics (QLVL), University of Leuven, Blijde-Inkomststraat 21 P.O. Box 3308, 3000 Leuven, Belgium"],"affiliations":[{"raw_affiliation_string":"Quantitative Lexicology and Variational Linguistics (QLVL), University of Leuven, Blijde-Inkomststraat 21 P.O. Box 3308, 3000 Leuven, Belgium","institution_ids":["https://openalex.org/I99464096"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5057289584"],"corresponding_institution_ids":["https://openalex.org/I2802067006","https://openalex.org/I99464096"],"apc_list":null,"apc_paid":null,"fwci":4.0594,"has_fulltext":false,"cited_by_count":63,"citation_normalized_percentile":{"value":0.93960438,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":93,"max":100},"biblio":{"volume":"16","issue":"4","first_page":"469","last_page":"491"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9986000061035156,"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/T10028","display_name":"Topic Modeling","score":0.9972000122070312,"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/computer-science","display_name":"Computer science","score":0.8447800278663635},{"id":"https://openalex.org/keywords/variation","display_name":"Variation (astronomy)","score":0.7966619729995728},{"id":"https://openalex.org/keywords/distributional-semantics","display_name":"Distributional semantics","score":0.7335642576217651},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6349372863769531},{"id":"https://openalex.org/keywords/terminology","display_name":"Terminology","score":0.6071171164512634},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5703659057617188},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.5526219606399536},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.5118133425712585},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.4930412471294403},{"id":"https://openalex.org/keywords/lexicography","display_name":"Lexicography","score":0.47126030921936035},{"id":"https://openalex.org/keywords/meaning","display_name":"Meaning (existential)","score":0.4615274965763092},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.43254294991493225},{"id":"https://openalex.org/keywords/lexical-semantics","display_name":"Lexical semantics","score":0.41056862473487854},{"id":"https://openalex.org/keywords/lexical-item","display_name":"Lexical item","score":0.3513956069946289},{"id":"https://openalex.org/keywords/semantic-similarity","display_name":"Semantic similarity","score":0.14842990040779114}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8447800278663635},{"id":"https://openalex.org/C2778334786","wikidata":"https://www.wikidata.org/wiki/Q1586270","display_name":"Variation (astronomy)","level":2,"score":0.7966619729995728},{"id":"https://openalex.org/C2778828372","wikidata":"https://www.wikidata.org/wiki/Q5283209","display_name":"Distributional semantics","level":3,"score":0.7335642576217651},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6349372863769531},{"id":"https://openalex.org/C547195049","wikidata":"https://www.wikidata.org/wiki/Q1725664","display_name":"Terminology","level":2,"score":0.6071171164512634},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5703659057617188},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.5526219606399536},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.5118133425712585},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.4930412471294403},{"id":"https://openalex.org/C80976798","wikidata":"https://www.wikidata.org/wiki/Q184524","display_name":"Lexicography","level":2,"score":0.47126030921936035},{"id":"https://openalex.org/C2780876879","wikidata":"https://www.wikidata.org/wiki/Q3054749","display_name":"Meaning (existential)","level":2,"score":0.4615274965763092},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.43254294991493225},{"id":"https://openalex.org/C98954769","wikidata":"https://www.wikidata.org/wiki/Q1759657","display_name":"Lexical semantics","level":3,"score":0.41056862473487854},{"id":"https://openalex.org/C126706616","wikidata":"https://www.wikidata.org/wiki/Q2944660","display_name":"Lexical item","level":2,"score":0.3513956069946289},{"id":"https://openalex.org/C130318100","wikidata":"https://www.wikidata.org/wiki/Q2268914","display_name":"Semantic similarity","level":2,"score":0.14842990040779114},{"id":"https://openalex.org/C44870925","wikidata":"https://www.wikidata.org/wiki/Q37547","display_name":"Astrophysics","level":1,"score":0.0},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C542102704","wikidata":"https://www.wikidata.org/wiki/Q183257","display_name":"Psychotherapist","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/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","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":2,"locations":[{"id":"doi:10.1017/s1351324910000161","is_oa":false,"landing_page_url":"https://doi.org/10.1017/s1351324910000161","pdf_url":null,"source":{"id":"https://openalex.org/S18088403","display_name":"Natural Language Engineering","issn_l":"1351-3249","issn":["1351-3249","1469-8110"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311721","host_organization_name":"Cambridge University Press","host_organization_lineage":["https://openalex.org/P4310311721","https://openalex.org/P4310311702"],"host_organization_lineage_names":["Cambridge University Press","University of Cambridge"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Natural Language Engineering","raw_type":"journal-article"},{"id":"pmh:oai:lirias2repo.kuleuven.be:123456789/287943","is_oa":false,"landing_page_url":"https://lirias.kuleuven.be/bitstream/123456789/287943/3/peirsman_geeraerts_speelman_2010final_automatic_identification_lexical.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306401954","display_name":"Lirias (KU Leuven)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I99464096","host_organization_name":"KU Leuven","host_organization_lineage":["https://openalex.org/I99464096"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Natural Language Engineering, vol. 16 (4), (469-491)","raw_type":"info:eu-repo/semantics/publishedVersion"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.800000011920929,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":65,"referenced_works":["https://openalex.org/W98685789","https://openalex.org/W137702406","https://openalex.org/W392761142","https://openalex.org/W631096649","https://openalex.org/W1479719301","https://openalex.org/W1495654639","https://openalex.org/W1512332532","https://openalex.org/W1570490112","https://openalex.org/W1578669249","https://openalex.org/W1593832660","https://openalex.org/W1651266083","https://openalex.org/W1657275562","https://openalex.org/W1662133657","https://openalex.org/W1836521361","https://openalex.org/W1956559956","https://openalex.org/W1983578042","https://openalex.org/W1995669683","https://openalex.org/W2005181355","https://openalex.org/W2006514889","https://openalex.org/W2008480878","https://openalex.org/W2015024653","https://openalex.org/W2037599344","https://openalex.org/W2041232209","https://openalex.org/W2050712820","https://openalex.org/W2064001888","https://openalex.org/W2080404274","https://openalex.org/W2081016167","https://openalex.org/W2091879664","https://openalex.org/W2095726049","https://openalex.org/W2102749417","https://openalex.org/W2107229268","https://openalex.org/W2111020819","https://openalex.org/W2116780029","https://openalex.org/W2130337399","https://openalex.org/W2139812240","https://openalex.org/W2140798747","https://openalex.org/W2142999328","https://openalex.org/W2144331291","https://openalex.org/W2163953154","https://openalex.org/W2164359605","https://openalex.org/W2166776180","https://openalex.org/W2168217710","https://openalex.org/W2274097489","https://openalex.org/W2325227998","https://openalex.org/W2498111210","https://openalex.org/W2498503852","https://openalex.org/W2500430820","https://openalex.org/W2511674125","https://openalex.org/W2520713908","https://openalex.org/W2524730743","https://openalex.org/W2524826419","https://openalex.org/W2563361074","https://openalex.org/W2618735189","https://openalex.org/W2781266681","https://openalex.org/W2789217505","https://openalex.org/W2882319491","https://openalex.org/W2912076133","https://openalex.org/W2979401726","https://openalex.org/W4205171160","https://openalex.org/W4211148787","https://openalex.org/W4214536890","https://openalex.org/W4251395411","https://openalex.org/W4299527668","https://openalex.org/W6674159460","https://openalex.org/W6677145740"],"related_works":["https://openalex.org/W2888105260","https://openalex.org/W1978008447","https://openalex.org/W2061150891","https://openalex.org/W143288845","https://openalex.org/W3083601245","https://openalex.org/W2017258330","https://openalex.org/W1718612490","https://openalex.org/W3167795126","https://openalex.org/W2040766353","https://openalex.org/W2104246881"],"abstract_inverted_index":{"Abstract":[0],"Languages":[1],"are":[2,104,128],"not":[3],"uniform.":[4],"Speakers":[5],"of":[6,35,48,65,71,76,90,99,106,112,118,149],"different":[7,21,78,147],"language":[8,79],"varieties":[9,80],"use":[10,74],"certain":[11],"words":[12,102],"differently":[13],"\u2013":[14],"more":[15,132],"or":[16,19,116,171],"less":[17],"frequently,":[18],"with":[20,165],"meanings.":[22],"We":[23,39,73],"argue":[24],"that":[25,103,125],"distributional":[26,66,126,157],"semantics":[27,158],"is":[28],"the":[29,33,49,68,83,97],"ideal":[30],"framework":[31],"for":[32,87],"investigation":[34],"such":[36],"lexical":[37,50],"variation.":[38,150],"address":[40,96],"two":[41,77],"research":[42,161],"questions":[43],"and":[44,55],"present":[45],"our":[46,153],"analysis":[47],"variation":[51],"between":[52],"Belgian":[53,92],"Dutch":[54,85],"Netherlandic":[56,84],"Dutch.":[57],"The":[58],"first":[59],"question":[60],"involves":[61],"a":[62,88,107,143,146],"classic":[63],"application":[64],"models:":[67],"automatic":[69],"retrieval":[70],"synonyms.":[72],"corpora":[75],"to":[81,130],"identify":[82,131],"synonyms":[86],"set":[89],"typically":[91],"words.":[93],"Second,":[94],"we":[95,123],"problem":[98],"automatically":[100],"identifying":[101],"typical":[105],"given":[108],"lect,":[109],"either":[110],"because":[111,117],"their":[113,119],"high":[114],"frequency":[115],"divergent":[120],"meaning.":[121],"Overall,":[122],"show":[124],"models":[127,140],"able":[129],"lectal":[133],"markers":[134],"than":[135],"traditional":[136],"keyword":[137],"methods.":[138],"Distributional":[139],"also":[141],"have":[142],"bias":[144],"towards":[145],"type":[148],"In":[151],"summary,":[152],"results":[154],"demonstrate":[155],"how":[156],"can":[159],"help":[160],"in":[162,169],"variational":[163],"linguistics,":[164],"possible":[166],"future":[167],"applications":[168],"lexicography":[170],"terminology":[172],"extraction.":[173]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":18},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":4},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":5},{"year":2014,"cited_by_count":7},{"year":2013,"cited_by_count":5},{"year":2012,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
