{"id":"https://openalex.org/W2125446229","doi":"https://doi.org/10.3115/v1/d14-1142","title":"Can characters reveal your native language? A language-independent approach to native language identification","display_name":"Can characters reveal your native language? A language-independent approach to native language identification","publication_year":2014,"publication_date":"2014-01-01","ids":{"openalex":"https://openalex.org/W2125446229","doi":"https://doi.org/10.3115/v1/d14-1142","mag":"2125446229"},"language":"en","primary_location":{"id":"doi:10.3115/v1/d14-1142","is_oa":true,"landing_page_url":"https://doi.org/10.3115/v1/d14-1142","pdf_url":"https://doi.org/10.3115/v1/d14-1142","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.3115/v1/d14-1142","any_repository_has_fulltext":null},"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":false,"raw_author_name":"Radu Tudor Ionescu","raw_affiliation_strings":["University of Bucharest, Bucharest, Romania"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Bucharest, Bucharest, Romania","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, Bucharest, Romania"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Bucharest, Bucharest, Romania","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/I20089843","display_name":"Princeton University","ror":"https://ror.org/00hx57361","country_code":"US","type":"education","lineage":["https://openalex.org/I20089843"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Aoife Cahill","raw_affiliation_strings":["Princeton University, Princeton, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Princeton University, Princeton, United States","institution_ids":["https://openalex.org/I20089843"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":8.0657,"has_fulltext":false,"cited_by_count":75,"citation_normalized_percentile":{"value":0.98446009,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"1363","last_page":"1373"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12380","display_name":"Authorship Attribution and Profiling","score":0.9998000264167786,"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/T12380","display_name":"Authorship Attribution and Profiling","score":0.9998000264167786,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9952999949455261,"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":0.9854000210762024,"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":0.819696307182312},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7253637313842773},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.629128634929657},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5513597726821899},{"id":"https://openalex.org/keywords/language-identification","display_name":"Language identification","score":0.5365680456161499},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.5353859663009644},{"id":"https://openalex.org/keywords/string","display_name":"String (physics)","score":0.5082477927207947},{"id":"https://openalex.org/keywords/categorization","display_name":"Categorization","score":0.4912495017051697},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.49003350734710693},{"id":"https://openalex.org/keywords/kernel-fisher-discriminant-analysis","display_name":"Kernel Fisher discriminant analysis","score":0.43411335349082947},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.4296090602874756},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.3552015423774719},{"id":"https://openalex.org/keywords/kernel-method","display_name":"Kernel method","score":0.32977333664894104},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.12207666039466858},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09318161010742188}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.819696307182312},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7253637313842773},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.629128634929657},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5513597726821899},{"id":"https://openalex.org/C129792486","wikidata":"https://www.wikidata.org/wiki/Q1050419","display_name":"Language identification","level":3,"score":0.5365680456161499},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.5353859663009644},{"id":"https://openalex.org/C157486923","wikidata":"https://www.wikidata.org/wiki/Q1376436","display_name":"String (physics)","level":2,"score":0.5082477927207947},{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.4912495017051697},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.49003350734710693},{"id":"https://openalex.org/C181367576","wikidata":"https://www.wikidata.org/wiki/Q6394184","display_name":"Kernel Fisher discriminant analysis","level":4,"score":0.43411335349082947},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.4296090602874756},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.3552015423774719},{"id":"https://openalex.org/C122280245","wikidata":"https://www.wikidata.org/wiki/Q620622","display_name":"Kernel method","level":3,"score":0.32977333664894104},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.12207666039466858},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09318161010742188},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","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/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"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/C37914503","wikidata":"https://www.wikidata.org/wiki/Q156495","display_name":"Mathematical physics","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.3115/v1/d14-1142","is_oa":true,"landing_page_url":"https://doi.org/10.3115/v1/d14-1142","pdf_url":"https://doi.org/10.3115/v1/d14-1142","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.671.6000","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.671.6000","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://emnlp2014.org/papers/pdf/EMNLP2014142.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.697.6415","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.697.6415","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://aclweb.org/anthology/D/D14/D14-1142.pdf","raw_type":"text"}],"best_oa_location":{"id":"doi:10.3115/v1/d14-1142","is_oa":true,"landing_page_url":"https://doi.org/10.3115/v1/d14-1142","pdf_url":"https://doi.org/10.3115/v1/d14-1142","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP)","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.6600000262260437}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W233152878","https://openalex.org/W1480376833","https://openalex.org/W1506915175","https://openalex.org/W1510073064","https://openalex.org/W1692377644","https://openalex.org/W1748131547","https://openalex.org/W1956641659","https://openalex.org/W2020733616","https://openalex.org/W2055011070","https://openalex.org/W2055699824","https://openalex.org/W2082439473","https://openalex.org/W2109158592","https://openalex.org/W2119821739","https://openalex.org/W2134380836","https://openalex.org/W2142387771","https://openalex.org/W2181262297","https://openalex.org/W2250876960","https://openalex.org/W2250987829","https://openalex.org/W2251303571","https://openalex.org/W2251370914","https://openalex.org/W2252160048","https://openalex.org/W2340746501","https://openalex.org/W2401457948","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W155772811","https://openalex.org/W2135267219","https://openalex.org/W226586525","https://openalex.org/W2905418897","https://openalex.org/W3033319502","https://openalex.org/W2129407254","https://openalex.org/W247270383","https://openalex.org/W2610521515","https://openalex.org/W2050029313","https://openalex.org/W1509134351"],"abstract_inverted_index":{"A":[0],"common":[1],"approach":[2,36,60,99,131,152],"in":[3,79,87,92,106,136],"text":[4,9],"mining":[5],"tasks":[6],"such":[7],"as":[8,41],"categorization,":[10],"authorship":[11],"identification":[12],"or":[13,26],"plagiarism":[14],"detection":[15],"is":[16,43,114,139],"to":[17],"rely":[18],"on":[19],"features":[20,42],"like":[21],"words,":[22],"part-of-speech":[23],"tags,":[24],"stems,":[25],"some":[27],"other":[28],"high-level":[29],"lin-guistic":[30],"features.":[31],"In":[32,146],"this":[33,93],"work,":[34],"an":[35,111,133],"that":[37,96,113,137,154],"uses":[38],"character":[39],"n-grams":[40],"proposed":[44,59,98,130,151],"for":[45],"the":[46,58,80,89,97,103,118,123,129,147,150,162,165],"task":[47],"of":[48,53,102,122,164],"native":[49,107],"language":[50,140],"identification.":[51],"Instead":[52],"doing":[54],"standard":[55],"feature":[56],"selection,":[57],"combines":[61],"several":[62],"string":[63],"kernels":[64],"using":[65],"mul-tiple":[66],"kernel":[67],"learning.":[68],"Kernel":[69,73],"Ridge":[70],"Re-gression":[71],"and":[72,142],"Discriminant":[74],"Analy-sis":[75],"are":[76],"independently":[77],"used":[78],"learning":[81],"stage.":[82],"The":[83],"empirical":[84],"results":[85],"obtained":[86],"all":[88],"experiments":[90],"conducted":[91],"work":[94],"in-dicate":[95],"achieves":[100],"state":[101,163],"art":[104,166],"performance":[105],"lan-guage":[108],"identification,":[109],"reaching":[110],"accuracy":[112],"1.7":[115],"%":[116],"above":[117],"top":[119],"scoring":[120],"system":[121,167],"2013":[124],"NLI":[125],"Shared":[126],"Task.":[127],"Further-more,":[128],"has":[132],"im-portant":[134],"advantage":[135],"it":[138,155],"in-dependent":[141],"linguistic":[143],"theory":[144],"neutral.":[145],"cross-corpus":[148],"experiment,":[149],"shows":[153],"can":[156],"also":[157],"be":[158],"topic":[159],"independent,":[160],"improving":[161],"by":[168],"32.3%.":[169],"1":[170]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":6},{"year":2018,"cited_by_count":12},{"year":2017,"cited_by_count":24},{"year":2016,"cited_by_count":9},{"year":2015,"cited_by_count":6},{"year":2013,"cited_by_count":1}],"updated_date":"2026-08-04T08:18:43.703281","created_date":"2025-10-10T00:00:00"}