{"id":"https://openalex.org/W2440817164","doi":"https://doi.org/10.1162/coli_a_00256","title":"String Kernels for Native Language Identification: Insights from Behind the Curtains","display_name":"String Kernels for Native Language Identification: Insights from Behind the Curtains","publication_year":2016,"publication_date":"2016-06-17","ids":{"openalex":"https://openalex.org/W2440817164","doi":"https://doi.org/10.1162/coli_a_00256","mag":"2440817164"},"language":"en","primary_location":{"id":"doi:10.1162/coli_a_00256","is_oa":true,"landing_page_url":"https://doi.org/10.1162/coli_a_00256","pdf_url":"https://www.mitpressjournals.org/doi/pdf/10.1162/COLI_a_00256","source":{"id":"https://openalex.org/S155526855","display_name":"Computational Linguistics","issn_l":"0891-2017","issn":["0891-2017","1530-9312"],"is_oa":false,"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computational Linguistics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://www.mitpressjournals.org/doi/pdf/10.1162/COLI_a_00256","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5081017623","display_name":"Radu Tudor Ionescu","orcid":"https://orcid.org/0000-0002-9301-1950"},"institutions":[{"id":"https://openalex.org/I141595442","display_name":"University of Bucharest","ror":"https://ror.org/02x2v6p15","country_code":"RO","type":"education","lineage":["https://openalex.org/I141595442"]}],"countries":["RO"],"is_corresponding":true,"raw_author_name":"Radu Tudor Ionescu","raw_affiliation_strings":["University of Bucharest"],"affiliations":[{"raw_affiliation_string":"University of Bucharest","institution_ids":["https://openalex.org/I141595442"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083743189","display_name":"Marius Popescu","orcid":"https://orcid.org/0000-0003-4158-3911"},"institutions":[{"id":"https://openalex.org/I141595442","display_name":"University of Bucharest","ror":"https://ror.org/02x2v6p15","country_code":"RO","type":"education","lineage":["https://openalex.org/I141595442"]}],"countries":["RO"],"is_corresponding":false,"raw_author_name":"Marius Popescu","raw_affiliation_strings":["University of Bucharest"],"affiliations":[{"raw_affiliation_string":"University of Bucharest","institution_ids":["https://openalex.org/I141595442"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5048408884","display_name":"Aoife Cahill","orcid":null},"institutions":[{"id":"https://openalex.org/I1341030882","display_name":"Educational Testing Service","ror":"https://ror.org/03b5q4637","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1341030882"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Aoife Cahill","raw_affiliation_strings":["Educational Testing Service"],"affiliations":[{"raw_affiliation_string":"Educational Testing Service","institution_ids":["https://openalex.org/I1341030882"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5081017623"],"corresponding_institution_ids":["https://openalex.org/I141595442"],"apc_list":null,"apc_paid":null,"fwci":13.6933,"has_fulltext":true,"cited_by_count":42,"citation_normalized_percentile":{"value":0.98753358,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"42","issue":"3","first_page":"491","last_page":"525"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9994999766349792,"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":0.9994999766349792,"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":0.9991000294685364,"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":0.9951000213623047,"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":0.8462257385253906},{"id":"https://openalex.org/keywords/string","display_name":"String (physics)","score":0.742618978023529},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6584994196891785},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6415603160858154},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.622635006904602},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6109756231307983},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5060433745384216},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.4857945442199707},{"id":"https://openalex.org/keywords/string-kernel","display_name":"String kernel","score":0.4463452994823456},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.42621898651123047},{"id":"https://openalex.org/keywords/kernel-method","display_name":"Kernel method","score":0.23410898447036743},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.11882692575454712},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.0876302421092987},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08282995223999023}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8462257385253906},{"id":"https://openalex.org/C157486923","wikidata":"https://www.wikidata.org/wiki/Q1376436","display_name":"String (physics)","level":2,"score":0.742618978023529},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6584994196891785},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6415603160858154},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.622635006904602},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6109756231307983},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5060433745384216},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.4857945442199707},{"id":"https://openalex.org/C55851704","wikidata":"https://www.wikidata.org/wiki/Q7623983","display_name":"String kernel","level":5,"score":0.4463452994823456},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.42621898651123047},{"id":"https://openalex.org/C122280245","wikidata":"https://www.wikidata.org/wiki/Q620622","display_name":"Kernel method","level":3,"score":0.23410898447036743},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.11882692575454712},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.0876302421092987},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08282995223999023},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C160446489","wikidata":"https://www.wikidata.org/wiki/Q7226642","display_name":"Polynomial kernel","level":4,"score":0.0},{"id":"https://openalex.org/C37914503","wikidata":"https://www.wikidata.org/wiki/Q156495","display_name":"Mathematical physics","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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1162/coli_a_00256","is_oa":true,"landing_page_url":"https://doi.org/10.1162/coli_a_00256","pdf_url":"https://www.mitpressjournals.org/doi/pdf/10.1162/COLI_a_00256","source":{"id":"https://openalex.org/S155526855","display_name":"Computational Linguistics","issn_l":"0891-2017","issn":["0891-2017","1530-9312"],"is_oa":false,"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computational Linguistics","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:c72ca3e89f8d4e9ba40d33fd3d486d86","is_oa":true,"landing_page_url":"https://doaj.org/article/c72ca3e89f8d4e9ba40d33fd3d486d86","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Computational Linguistics, Vol 42, Iss 3 (2024)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1162/coli_a_00256","is_oa":true,"landing_page_url":"https://doi.org/10.1162/coli_a_00256","pdf_url":"https://www.mitpressjournals.org/doi/pdf/10.1162/COLI_a_00256","source":{"id":"https://openalex.org/S155526855","display_name":"Computational Linguistics","issn_l":"0891-2017","issn":["0891-2017","1530-9312"],"is_oa":false,"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computational Linguistics","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.5600000023841858}],"awards":[{"id":"https://openalex.org/G3998201246","display_name":null,"funder_award_id":"Social","funder_id":"https://openalex.org/F4320338080","funder_display_name":"European Social Fund"}],"funders":[{"id":"https://openalex.org/F4320323078","display_name":"Universitetet i Bergen","ror":"https://ror.org/03zga2b32"},{"id":"https://openalex.org/F4320338080","display_name":"European Social Fund","ror":"https://ror.org/00k4n6c32"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2440817164.pdf","grobid_xml":"https://content.openalex.org/works/W2440817164.grobid-xml"},"referenced_works_count":56,"referenced_works":["https://openalex.org/W233152878","https://openalex.org/W314203818","https://openalex.org/W628213742","https://openalex.org/W1014657286","https://openalex.org/W1480376833","https://openalex.org/W1480643256","https://openalex.org/W1505640402","https://openalex.org/W1506915175","https://openalex.org/W1510073064","https://openalex.org/W1532325895","https://openalex.org/W1554216175","https://openalex.org/W1576213419","https://openalex.org/W1687791635","https://openalex.org/W1692377644","https://openalex.org/W1748131547","https://openalex.org/W1979106445","https://openalex.org/W2006608939","https://openalex.org/W2020733616","https://openalex.org/W2029964106","https://openalex.org/W2034264652","https://openalex.org/W2055011070","https://openalex.org/W2055699824","https://openalex.org/W2082439473","https://openalex.org/W2099763641","https://openalex.org/W2109158592","https://openalex.org/W2109625801","https://openalex.org/W2109743529","https://openalex.org/W2119821739","https://openalex.org/W2125257468","https://openalex.org/W2125446229","https://openalex.org/W2134380836","https://openalex.org/W2137264748","https://openalex.org/W2140266767","https://openalex.org/W2142387771","https://openalex.org/W2154121272","https://openalex.org/W2155701129","https://openalex.org/W2169087896","https://openalex.org/W2181262297","https://openalex.org/W2250272113","https://openalex.org/W2250326993","https://openalex.org/W2250876960","https://openalex.org/W2250987829","https://openalex.org/W2251303571","https://openalex.org/W2251499136","https://openalex.org/W2252113867","https://openalex.org/W2252160048","https://openalex.org/W2340746501","https://openalex.org/W2398873259","https://openalex.org/W2401457948","https://openalex.org/W2402118036","https://openalex.org/W2556949068","https://openalex.org/W2591059568","https://openalex.org/W2759600630","https://openalex.org/W4239510810","https://openalex.org/W4246066915","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W152351265","https://openalex.org/W3042295250","https://openalex.org/W2142835450","https://openalex.org/W2068282877","https://openalex.org/W1558063662","https://openalex.org/W2278188209","https://openalex.org/W4226175139","https://openalex.org/W166328336","https://openalex.org/W2351655457","https://openalex.org/W1753959513"],"abstract_inverted_index":{"The":[0,46,169,252,317,340,390],"most":[1],"common":[2],"approach":[3,27,47,65,89,111,140,164,186,225,278,406,414],"in":[4,173,179,190,272,314],"text":[5],"mining":[6],"classification":[7],"tasks":[8],"is":[9,82,112,128,196,226,396],"to":[10,114,120,134,142,159,360,397],"rely":[11],"on":[12,67,124,213,257,411],"features":[13,34,303,329,341],"like":[14],"words,":[15,99,350],"part-of-speech":[16],"tags,":[17],"stems,":[18,348],"or":[19,103],"some":[20,409],"other":[21,166],"high-level":[22],"linguistic":[23],"features.":[24,365],"Recently,":[25],"an":[26,129,193,239],"that":[28,63,97,132,183,195,222,280],"uses":[29],"only":[30],"character":[31],"p-grams":[32,336],"as":[33,308],"has":[35],"been":[36,123],"proposed":[37,185,224,277,333],"for":[38],"the":[39,61,64,110,137,144,161,176,184,199,204,210,215,218,223,230,246,267,276,288,298,302,306,328,332,344,358,368,393,403],"task":[40],"of":[41,152,175,203,241,254,337,378,392,402],"native":[42,153,232,259],"language":[43,116,154,227,233,260,324,379],"identification":[44,155,234,261],"(NLI).":[45],"obtained":[48,172,212],"state-of-the-art":[49,167,188,268,289],"results":[50,171,211,253],"by":[51,291,305,331,343],"combining":[52],"several":[53,73],"string":[54,68,138,162,236,255,299,404],"kernels":[55,69,163,237,256,300,405],"using":[56],"multiple":[57],"kernel":[58,139],"learning.":[59],"Despite":[60],"fact":[62],"based":[66],"performs":[70],"so":[71,250,416],"well,":[72],"questions":[74,146],"about":[75,297,322],"this":[76,180,315,371,413],"method":[77],"remain":[78],"unanswered.":[79],"First,":[80],"it":[81,281],"not":[83],"clear":[84],"why":[85,412],"such":[86],"a":[87,273,399],"simple":[88],"can":[90,282],"compete":[91],"with":[92,165],"far":[93],"more":[94,242,310],"complex":[95],"approaches":[96],"take":[98],"lemmas,":[100],"syntactic":[101],"information,":[102],"even":[104],"semantics":[105],"into":[106,375],"account.":[107],"Second,":[108],"although":[109],"designed":[113],"be":[115,284],"independent,":[117,286],"all":[118,174],"experiments":[119,156,177],"date":[121],"have":[122,357],"English.":[125],"This":[126],"work":[127,181],"extensive":[130],"study":[131,395],"aims":[133],"systematically":[135],"present":[136],"and":[141,217,351,354,387,407],"clarify":[143],"open":[145],"mentioned":[147],"above.":[148],"A":[149],"broad":[150],"set":[151],"were":[157],"conducted":[158,178],"compare":[160],"methods.":[168],"empirical":[170],"indicate":[182],"achieves":[187],"performance":[189],"NLI,":[191],"reaching":[192],"accuracy":[194,248],"1.7%":[197],"above":[198],"top":[200],"scoring":[201],"system":[202,290],"2013":[205],"NLI":[206],"Shared":[207],"Task.":[208],"Furthermore,":[209],"both":[214],"Arabic":[216,231],"Norwegian":[219,258],"corpora":[220],"demonstrate":[221],"independent.":[228],"In":[229,270],"task,":[235],"show":[238],"increase":[240],"than":[243,266],"17%":[244],"over":[245,362],"best":[247],"reported":[249],"far.":[251],"are":[262,312,335],"also":[263,283,319],"significantly":[264],"better":[265],"approach.":[269],"addition,":[271],"cross-corpus":[274],"experiment,":[275],"shows":[279],"topic":[285],"improving":[287],"32.3%.":[292],"To":[293],"gain":[294],"additional":[295],"insights":[296,374],"approach,":[301],"selected":[304],"classifier":[307],"being":[309],"discriminating":[311,369],"analyzed":[313],"work.":[316],"analysis":[318],"offers":[320,373],"information":[321],"localized":[323],"transfer":[325,380],"effects,":[326,381],"since":[327],"used":[330],"model":[334,345],"various":[338],"lengths.":[339],"captured":[342],"typically":[346],"include":[347],"function":[349],"word":[352,383],"prefixes":[353],"suffixes,":[355],"which":[356],"potential":[359],"generalize":[361],"purely":[363],"word-based":[364],"By":[366],"analyzing":[367],"features,":[370],"article":[372],"two":[376],"kinds":[377],"namely,":[382],"choice":[384],"(lexical":[385],"transfer)":[386],"morphological":[388],"differences.":[389],"goal":[391],"current":[394],"give":[398],"full":[400],"view":[401],"shed":[408],"light":[410],"works":[415],"well.":[417]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":6},{"year":2018,"cited_by_count":12},{"year":2017,"cited_by_count":9},{"year":2016,"cited_by_count":4}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}