{"id":"https://openalex.org/W2081748579","doi":"https://doi.org/10.1080/09296170500500694","title":"Language identification from small text samples*","display_name":"Language identification from small text samples*","publication_year":2006,"publication_date":"2006-01-01","ids":{"openalex":"https://openalex.org/W2081748579","doi":"https://doi.org/10.1080/09296170500500694","mag":"2081748579"},"language":"en","primary_location":{"id":"doi:10.1080/09296170500500694","is_oa":false,"landing_page_url":"https://doi.org/10.1080/09296170500500694","pdf_url":null,"source":{"id":"https://openalex.org/S24321443","display_name":"Journal of Quantitative Linguistics","issn_l":"0929-6174","issn":["0929-6174","1744-5035"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319847","host_organization_name":"Routledge","host_organization_lineage":["https://openalex.org/P4310319847"],"host_organization_lineage_names":["Routledge"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Quantitative Linguistics","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/A5109529933","display_name":"K. N. Balasubramanya Murthy","orcid":null},"institutions":[{"id":"https://openalex.org/I36893310","display_name":"University of Hyderabad","ror":"https://ror.org/04a7rxb17","country_code":"IN","type":"education","lineage":["https://openalex.org/I36893310"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Kavi Narayana Murthy","raw_affiliation_strings":["University of Hyderabad","Dept. of Computer and Information Sciences, University of Hyderabad, India"],"affiliations":[{"raw_affiliation_string":"University of Hyderabad","institution_ids":["https://openalex.org/I36893310"]},{"raw_affiliation_string":"Dept. of Computer and Information Sciences, University of Hyderabad, India","institution_ids":["https://openalex.org/I36893310"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5039894381","display_name":"G. Bharadwaja Kumar","orcid":null},"institutions":[{"id":"https://openalex.org/I36893310","display_name":"University of Hyderabad","ror":"https://ror.org/04a7rxb17","country_code":"IN","type":"education","lineage":["https://openalex.org/I36893310"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"G. Bharadwaja Kumar","raw_affiliation_strings":["University of Hyderabad","Dept. of Computer and Information Sciences, University of Hyderabad, India"],"affiliations":[{"raw_affiliation_string":"University of Hyderabad","institution_ids":["https://openalex.org/I36893310"]},{"raw_affiliation_string":"Dept. of Computer and Information Sciences, University of Hyderabad, India","institution_ids":["https://openalex.org/I36893310"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5109529933"],"corresponding_institution_ids":["https://openalex.org/I36893310"],"apc_list":null,"apc_paid":null,"fwci":2.7105,"has_fulltext":false,"cited_by_count":55,"citation_normalized_percentile":{"value":0.90600478,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"13","issue":"1","first_page":"57","last_page":"80"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12380","display_name":"Authorship Attribution and Profiling","score":0.9965999722480774,"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":0.9965999722480774,"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":0.9911999702453613,"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/T10759","display_name":"Translation Studies and Practices","score":0.9495999813079834,"subfield":{"id":"https://openalex.org/subfields/1203","display_name":"Language and Linguistics"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/telugu","display_name":"Telugu","score":0.8991010189056396},{"id":"https://openalex.org/keywords/malayalam","display_name":"Malayalam","score":0.7683365345001221},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.767327070236206},{"id":"https://openalex.org/keywords/hindi","display_name":"Hindi","score":0.7286427021026611},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6991190314292908},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.6913211345672607},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6893505454063416},{"id":"https://openalex.org/keywords/language-identification","display_name":"Language identification","score":0.6520038843154907},{"id":"https://openalex.org/keywords/bengali","display_name":"Bengali","score":0.6096673607826233},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.4819643199443817},{"id":"https://openalex.org/keywords/tamil","display_name":"Tamil","score":0.45849597454071045},{"id":"https://openalex.org/keywords/language-family","display_name":"Language family","score":0.41909271478652954},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.2900125980377197},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.23935368657112122},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.08606904745101929}],"concepts":[{"id":"https://openalex.org/C2778756302","wikidata":"https://www.wikidata.org/wiki/Q8097","display_name":"Telugu","level":2,"score":0.8991010189056396},{"id":"https://openalex.org/C2779662586","wikidata":"https://www.wikidata.org/wiki/Q36236","display_name":"Malayalam","level":2,"score":0.7683365345001221},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.767327070236206},{"id":"https://openalex.org/C519982507","wikidata":"https://www.wikidata.org/wiki/Q1568","display_name":"Hindi","level":2,"score":0.7286427021026611},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6991190314292908},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.6913211345672607},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6893505454063416},{"id":"https://openalex.org/C129792486","wikidata":"https://www.wikidata.org/wiki/Q1050419","display_name":"Language identification","level":3,"score":0.6520038843154907},{"id":"https://openalex.org/C19235068","wikidata":"https://www.wikidata.org/wiki/Q9610","display_name":"Bengali","level":2,"score":0.6096673607826233},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.4819643199443817},{"id":"https://openalex.org/C140688305","wikidata":"https://www.wikidata.org/wiki/Q5885","display_name":"Tamil","level":2,"score":0.45849597454071045},{"id":"https://openalex.org/C2780566098","wikidata":"https://www.wikidata.org/wiki/Q25295","display_name":"Language family","level":2,"score":0.41909271478652954},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.2900125980377197},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.23935368657112122},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.08606904745101929},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1080/09296170500500694","is_oa":false,"landing_page_url":"https://doi.org/10.1080/09296170500500694","pdf_url":null,"source":{"id":"https://openalex.org/S24321443","display_name":"Journal of Quantitative Linguistics","issn_l":"0929-6174","issn":["0929-6174","1744-5035"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319847","host_organization_name":"Routledge","host_organization_lineage":["https://openalex.org/P4310319847"],"host_organization_lineage_names":["Routledge"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Quantitative Linguistics","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.8500000238418579,"display_name":"Quality Education"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320320767","display_name":"University Grants Commission","ror":"https://ror.org/04p800546"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W177632497","https://openalex.org/W1511336021","https://openalex.org/W1552061030","https://openalex.org/W1572370751","https://openalex.org/W1983072039","https://openalex.org/W2014296507","https://openalex.org/W2036400974","https://openalex.org/W2042074090","https://openalex.org/W2093321708","https://openalex.org/W2151773777","https://openalex.org/W2178472575","https://openalex.org/W2288874616","https://openalex.org/W2289041015","https://openalex.org/W2556956186","https://openalex.org/W2797532987","https://openalex.org/W2798214469","https://openalex.org/W3088771483","https://openalex.org/W4285719527","https://openalex.org/W4299857007"],"related_works":["https://openalex.org/W379929139","https://openalex.org/W654102581","https://openalex.org/W400493711","https://openalex.org/W565111942","https://openalex.org/W2475778260","https://openalex.org/W2250750541","https://openalex.org/W2537838974","https://openalex.org/W4240381670","https://openalex.org/W2015787804","https://openalex.org/W4293229170"],"abstract_inverted_index":{"Abstract":[0],"There":[1],"is":[2,55,62,75,101,153,235,303],"an":[3,57],"increasing":[4],"need":[5],"to":[6,160,186,225,237],"deal":[7],"with":[8,223],"multi-lingual":[9,16],"documents":[10,17],"today.":[11],"If":[12],"we":[13],"could":[14],"segment":[15,42],"language-wise,":[18],"it":[19],"would":[20],"be":[21,113],"very":[22],"useful":[23],"both":[24],"for":[25,37,98,106,115,127,135,142,146,242],"exploration":[26],"of":[27,40,46,53,123,139,150,182,198,227,245,250,267,290,296,300,306,320,332],"linguistic":[28],"phenomena,":[29],"such":[30],"as":[31,43,77,263],"code-switching":[32],"and":[33,36,108,145,179,215],"code":[34],"mixing,":[35],"computational":[38],"processing":[39],"each":[41],"appropriate.":[44],"Identification":[45],"language":[47,64,73,163,217,255,345],"from":[48,66,92,194],"a":[49,78,84,93,102,120,129,205,281,307],"given":[50],"small":[51,67],"piece":[52],"text":[54,68,333],"therefore":[56],"important":[58],"problem.":[59,132],"This":[60,117],"paper":[61,118],"about":[63],"identification":[65,74,164,201,256,346],"samples.":[69],"In":[70,248],"this":[71,315,348],"paper,":[72,316],"formulated":[76],"generic":[79],"machine":[80],"learning":[81],"problem":[82,208],"\u2013":[83],"supervised":[85],"classification":[86,131],"task":[87,144],"in":[88,209,254,274,280,314,334],"which":[89],"features":[90,152],"extracted":[91],"training":[94],"corpus":[95],"are":[96,271,292,327],"used":[97,114],"classification.":[99,116],"Regression":[100,110],"well":[103],"established":[104],"technique":[105],"modelling":[107],"analysis.":[109],"can":[111],"also":[112,231],"gives":[119],"clear":[121],"formulation":[122],"multiple":[124],"linear":[125],"regression":[126],"solving":[128],"two-class":[130],"Theoretical":[133],"bases":[134],"verifying":[136],"the":[137,140,143,148,187,191,195,210,238,246,251,264,297,304,318,328],"adequacy":[138],"model":[141],"analysing":[147],"significance":[149],"individual":[151],"included.":[154],"The":[155,287,310],"method":[156],"has":[157],"been":[158,220,232,261],"applied":[159],"pair":[161],"wise":[162],"among":[165],"several":[166],"major":[167],"Indian":[168,211,269,301,335],"languages":[169,184,244],"including":[170],"Hindi,":[171],"Bengali,":[172],"Marathi,":[173],"Punjabi,":[174],"Oriya,":[175],"Telugu,":[176],"Tamil,":[177],"Malayalam":[178],"Kannada.":[180],"Some":[181],"these":[183],"belong":[185],"Indo-Aryan":[188],"family":[189,197],"while":[190],"others":[192],"come":[193],"Dravidian":[196],"languages.":[199],"Language":[200],"was":[202],"so":[203,257],"far":[204],"largely":[206],"unexplored":[207],"context.":[212],"Variations":[213,222],"within":[214],"across":[216],"families":[218],"have":[219,230,260],"explored.":[221,233],"regard":[224],"sizes":[226],"test":[228],"samples":[229],"Performance":[234],"comparable":[236],"best":[239],"published":[240,252],"results":[241,343],"other":[243],"world.":[247],"most":[249],"work":[253],"far,":[258],"bytes":[259],"taken":[262],"fundamental":[265,288],"units":[266,279,289,331],"text.":[268],"scripts":[270,302],"primarily":[272],"syllabic":[273],"nature,":[275],"reflecting":[276],"phonetic":[277],"sound":[278],"more":[282,329],"or":[283,339],"less":[284],"direct":[285],"fashion.":[286],"writing":[291],"called":[293],"aksharas.":[294,322],"One":[295],"unique":[298],"characteristics":[299],"concept":[305],"script":[308,311],"grammar.":[309],"grammar,":[312],"included":[313],"defines":[317],"set":[319],"valid":[321],"We":[323],"hypothesize":[324],"that":[325],"aksharas":[326],"appropriate":[330],"languages,":[336],"not":[337],"characters":[338],"bytes.":[340],"Our":[341],"experimental":[342],"on":[344],"support":[347],"claim.":[349]},"counts_by_year":[{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":5},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":4},{"year":2014,"cited_by_count":7},{"year":2013,"cited_by_count":3},{"year":2012,"cited_by_count":3}],"updated_date":"2026-02-08T09:19:03.324500","created_date":"2025-10-10T00:00:00"}