{"id":"https://openalex.org/W2963095156","doi":"https://doi.org/10.1162/coli_a_00293","title":"A Kernel Independence Test for Geographical Language Variation","display_name":"A Kernel Independence Test for Geographical Language Variation","publication_year":2017,"publication_date":"2017-06-09","ids":{"openalex":"https://openalex.org/W2963095156","doi":"https://doi.org/10.1162/coli_a_00293","mag":"2963095156"},"language":"en","primary_location":{"is_oa":true,"landing_page_url":"https://doi.org/10.1162/coli_a_00293","pdf_url":"https://www.mitpressjournals.org/doi/pdf/10.1162/COLI_a_00293","source":{"id":"https://openalex.org/S155526855","display_name":"Computational Linguistics","issn_l":"0891-2017","issn":["0891-2017","1530-9312"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true},"type":"article","type_crossref":"journal-article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://www.mitpressjournals.org/doi/pdf/10.1162/COLI_a_00293","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5004209770","display_name":"Dong Nguyen","orcid":"https://orcid.org/0000-0002-6062-3117"},"institutions":[{"id":"https://openalex.org/I94624287","display_name":"University of Twente","ror":"https://ror.org/006hf6230","country_code":"NL","type":"education","lineage":["https://openalex.org/I94624287"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Dong Nguyen","raw_affiliation_strings":["University of Twente"],"affiliations":[{"raw_affiliation_string":"University of Twente","institution_ids":["https://openalex.org/I94624287"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5047699861","display_name":"Jacob Eisenstein","orcid":null},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jacob Eisenstein","raw_affiliation_strings":["Georgia Institute of Technology"],"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology","institution_ids":["https://openalex.org/I130701444"]}]}],"institution_assertions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":0,"currency":"USD","value_usd":0,"provenance":"doaj"},"apc_paid":null,"fwci":10.409,"has_fulltext":true,"fulltext_origin":"pdf","cited_by_count":19,"citation_normalized_percentile":{"value":0.999811,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":91},"biblio":{"volume":"43","issue":"3","first_page":"567","last_page":"592"},"is_retracted":false,"is_paratext":false,"primary_topic":{"id":"https://openalex.org/T11640","display_name":"Linguistic Variation and Morphology","score":0.9934,"subfield":{"id":"https://openalex.org/subfields/3310","display_name":"Linguistics and Language"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11640","display_name":"Linguistic Variation and Morphology","score":0.9934,"subfield":{"id":"https://openalex.org/subfields/3310","display_name":"Linguistics and Language"},"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/T11911","display_name":"Spatial and Panel Data Analysis","score":0.9764,"subfield":{"id":"https://openalex.org/subfields/2002","display_name":"Economics and Econometrics"},"field":{"id":"https://openalex.org/fields/20","display_name":"Economics, Econometrics and Finance"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T13910","display_name":"Computational and Text Analysis Methods","score":0.9225,"subfield":{"id":"https://openalex.org/subfields/3300","display_name":"General Social Sciences"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/variation","display_name":"Variation (astronomy)","score":0.566983}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.67063355},{"id":"https://openalex.org/C102366305","wikidata":"https://www.wikidata.org/wiki/Q1097688","display_name":"Nonparametric statistics","level":2,"score":0.5868644},{"id":"https://openalex.org/C2778334786","wikidata":"https://www.wikidata.org/wiki/Q1586270","display_name":"Variation (astronomy)","level":2,"score":0.566983},{"id":"https://openalex.org/C80884492","wikidata":"https://www.wikidata.org/wiki/Q3345678","display_name":"Reproducing kernel Hilbert space","level":3,"score":0.5418324},{"id":"https://openalex.org/C117251300","wikidata":"https://www.wikidata.org/wiki/Q1849855","display_name":"Parametric statistics","level":2,"score":0.45468852},{"id":"https://openalex.org/C169857963","wikidata":"https://www.wikidata.org/wiki/Q1461038","display_name":"Test statistic","level":3,"score":0.43634808},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.41386068},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40060645},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3653112},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.25885168},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.2418935},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.23195267},{"id":"https://openalex.org/C87007009","wikidata":"https://www.wikidata.org/wiki/Q210832","display_name":"Statistical hypothesis testing","level":2,"score":0.21992823},{"id":"https://openalex.org/C62799726","wikidata":"https://www.wikidata.org/wiki/Q190056","display_name":"Hilbert space","level":2,"score":0.09266883},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","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/C44870925","wikidata":"https://www.wikidata.org/wiki/Q37547","display_name":"Astrophysics","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}],"mesh":[],"locations_count":4,"locations":[{"is_oa":true,"landing_page_url":"https://doi.org/10.1162/coli_a_00293","pdf_url":"https://www.mitpressjournals.org/doi/pdf/10.1162/COLI_a_00293","source":{"id":"https://openalex.org/S155526855","display_name":"Computational Linguistics","issn_l":"0891-2017","issn":["0891-2017","1530-9312"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true},{"is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/portal/en/publications/a-kernel-independence-test-for-geographical-language-variation(b58b6213-5b4c-48f1-91eb-8bb9fa676061).html","pdf_url":"https://www.research.ed.ac.uk/files/33401508/nguyen_eisenstein_2.pdf","source":{"id":"https://openalex.org/S4306400320","display_name":"Edinburgh Research Explorer (University of Edinburgh)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I98677209","host_organization_name":"University of Edinburgh","host_organization_lineage":["https://openalex.org/I98677209"],"host_organization_lineage_names":["University of Edinburgh"],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"acceptedVersion","is_accepted":true,"is_published":false},{"is_oa":true,"landing_page_url":"https://www.pure.ed.ac.uk/ws/files/33401508/nguyen_eisenstein_2.pdf","pdf_url":"https://www.pure.ed.ac.uk/ws/files/33401508/nguyen_eisenstein_2.pdf","source":{"id":"https://openalex.org/S4306400321","display_name":"Edinburgh Research Explorer (University of Edinburgh)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I98677209","host_organization_name":"University of Edinburgh","host_organization_lineage":["https://openalex.org/I98677209"],"host_organization_lineage_names":["University of Edinburgh"],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"acceptedVersion","is_accepted":true,"is_published":false},{"is_oa":true,"landing_page_url":"https://arxiv.org/abs/1601.06579","pdf_url":"https://arxiv.org/pdf/1601.06579","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":["Cornell University"],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false}],"best_oa_location":{"is_oa":true,"landing_page_url":"https://doi.org/10.1162/coli_a_00293","pdf_url":"https://www.mitpressjournals.org/doi/pdf/10.1162/COLI_a_00293","source":{"id":"https://openalex.org/S155526855","display_name":"Computational Linguistics","issn_l":"0891-2017","issn":["0891-2017","1530-9312"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true},"sustainable_development_goals":[{"score":0.74,"id":"https://metadata.un.org/sdg/4","display_name":"Quality education"}],"grants":[],"datasets":[],"versions":[],"referenced_works_count":52,"referenced_works":["https://openalex.org/W1015972382","https://openalex.org/W1510073064","https://openalex.org/W1517859636","https://openalex.org/W1530343883","https://openalex.org/W1638081485","https://openalex.org/W1931677568","https://openalex.org/W1946269420","https://openalex.org/W1977495787","https://openalex.org/W1979839410","https://openalex.org/W1981145803","https://openalex.org/W2002722861","https://openalex.org/W2019896668","https://openalex.org/W2025403586","https://openalex.org/W2046222983","https://openalex.org/W2052611179","https://openalex.org/W2066759958","https://openalex.org/W2084956789","https://openalex.org/W2084974857","https://openalex.org/W2093601069","https://openalex.org/W2100265804","https://openalex.org/W2100600008","https://openalex.org/W2102637390","https://openalex.org/W2105465844","https://openalex.org/W2108545867","https://openalex.org/W2110065044","https://openalex.org/W2110097068","https://openalex.org/W2112552549","https://openalex.org/W2118898434","https://openalex.org/W2121981114","https://openalex.org/W2124101779","https://openalex.org/W2127658298","https://openalex.org/W2127713198","https://openalex.org/W2131586477","https://openalex.org/W2137435333","https://openalex.org/W2142889507","https://openalex.org/W2145544165","https://openalex.org/W2149510050","https://openalex.org/W2165442870","https://openalex.org/W2170199215","https://openalex.org/W2234751941","https://openalex.org/W2251157848","https://openalex.org/W2251263615","https://openalex.org/W2253444830","https://openalex.org/W2286250368","https://openalex.org/W2397481274","https://openalex.org/W2463154922","https://openalex.org/W3098520516","https://openalex.org/W3101183984","https://openalex.org/W3126122061","https://openalex.org/W3140093673","https://openalex.org/W4254587507","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W4223419583","https://openalex.org/W3188039121","https://openalex.org/W3107474891","https://openalex.org/W2266255878","https://openalex.org/W2128522844","https://openalex.org/W2099223682","https://openalex.org/W2026442432","https://openalex.org/W2014857050","https://openalex.org/W1990483788","https://openalex.org/W137543016"],"abstract_inverted_index":{"Quantifying":[0],"the":[1,39,104,161],"degree":[2],"of":[3,30,53,66,86,106,115,141,147,158,180,184],"spatial":[4],"dependence":[5],"for":[6,13,78,99],"linguistic":[7,54,69],"variables":[8],"is":[9,71,111,170],"a":[10,68,75,107,138,145,150,155,177],"key":[11],"task":[12],"analyzing":[14],"dialectal":[15],"variation.":[16],"However,":[17],"existing":[18],"approaches":[19,57],"have":[20],"important":[21],"drawbacks.":[22],"First,":[23],"they":[24,46],"are":[25,43,47],"based":[26],"on":[27,92],"parametric":[28,41],"models":[29],"dependence,":[31],"which":[32,83],"limits":[33],"their":[34],"power":[35],"in":[36,163],"cases":[37],"where":[38],"underlying":[40],"assumptions":[42],"violated.":[44],"Second,":[45],"not":[48],"applicable":[49],"to":[50,60,63,160,172],"all":[51],"types":[52,183],"data:":[55],"Some":[56],"apply":[58],"only":[59],"frequencies,":[61],"others":[62],"boolean":[64],"indicators":[65],"whether":[67],"variable":[70],"present.":[72],"We":[73,125],"present":[74],"new":[76],"method":[77],"measuring":[79],"geographical":[80,123],"language":[81],"variation,":[82],"solves":[84],"both":[85],"these":[87],"problems.":[88],"Our":[89,167],"approach":[90],"builds":[91],"Reproducing":[93],"Kernel":[94],"Hilbert":[95],"Space":[96],"(RKHS)":[97],"representations":[98],"nonparametric":[100],"statistics,":[101],"and":[102,154,182],"takes":[103],"form":[105],"test":[108,128,169],"statistic":[109],"that":[110],"computed":[112],"from":[113],"pairs":[114],"individual":[116],"geotagged":[117],"observations":[118],"without":[119],"aggregation":[120],"into":[121],"predefined":[122],"bins.":[124],"compare":[126],"this":[127],"with":[129],"prior":[130],"work":[131],"using":[132],"synthetic":[133],"data":[134,143,156],"as":[135,137],"well":[136],"diverse":[139],"set":[140,157],"real":[142],"sets:":[144],"corpus":[146],"Dutch":[148,151],"tweets,":[149],"syntactic":[152],"atlas,":[153],"letters":[159],"editor":[162],"North":[164],"American":[165],"newspapers.":[166],"proposed":[168],"shown":[171],"support":[173],"robust":[174],"inferences":[175],"across":[176],"broad":[178],"range":[179],"scenarios":[181],"data.":[185]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W2963095156","counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":3}],"updated_date":"2024-12-19T09:59:43.765411","created_date":"2019-07-30"}