{"id":"https://openalex.org/W2147777361","doi":"https://doi.org/10.1017/s135132490200284x","title":"A statistical information extraction system for Turkish","display_name":"A statistical information extraction system for Turkish","publication_year":2003,"publication_date":"2003-06-01","ids":{"openalex":"https://openalex.org/W2147777361","doi":"https://doi.org/10.1017/s135132490200284x","mag":"2147777361"},"language":"en","primary_location":{"id":"doi:10.1017/s135132490200284x","is_oa":false,"landing_page_url":"https://doi.org/10.1017/s135132490200284x","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":true,"oa_status":"green","oa_url":"http://hdl.handle.net/11693/18581","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5087941479","display_name":"G\u00f6khan T\u00fcr","orcid":"https://orcid.org/0009-0008-7740-2557"},"institutions":[{"id":"https://openalex.org/I1283103587","display_name":"AT&T (United States)","ror":"https://ror.org/02bbd5539","country_code":"US","type":"company","lineage":["https://openalex.org/I1283103587"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"G\u00d6KHAN T\u00dcR","raw_affiliation_strings":["AT&T Labs \u2013 Research, 180 Park Avenue, Florham Park, NJ 07932, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AT&T Labs \u2013 Research, 180 Park Avenue, Florham Park, NJ 07932, USA","institution_ids":["https://openalex.org/I1283103587"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068709817","display_name":"Dilek Hakkani\u2010T\u00fcr","orcid":null},"institutions":[{"id":"https://openalex.org/I1283103587","display_name":"AT&T (United States)","ror":"https://ror.org/02bbd5539","country_code":"US","type":"company","lineage":["https://openalex.org/I1283103587"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"DILEK HAKKANI-T\u00dcR","raw_affiliation_strings":["AT&T Labs \u2013 Research, 180 Park Avenue, Florham Park, NJ 07932, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AT&T Labs \u2013 Research, 180 Park Avenue, Florham Park, NJ 07932, USA","institution_ids":["https://openalex.org/I1283103587"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5003566053","display_name":"Kemal Oflazer","orcid":"https://orcid.org/0000-0002-4977-0079"},"institutions":[{"id":"https://openalex.org/I134235054","display_name":"Sabanc\u0131 \u00dcniversitesi","ror":"https://ror.org/049asqa32","country_code":"TR","type":"education","lineage":["https://openalex.org/I134235054"]}],"countries":["TR"],"is_corresponding":false,"raw_author_name":"KEMAL OFLAZER","raw_affiliation_strings":["Faculty of Engineering and Natural Sciences, Sabanci University, Istanbul TR-81474, Turkey"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Engineering and Natural Sciences, Sabanci University, Istanbul TR-81474, Turkey","institution_ids":["https://openalex.org/I134235054"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.9289,"has_fulltext":false,"cited_by_count":112,"citation_normalized_percentile":{"value":0.82215519,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":"9","issue":"2","first_page":"181","last_page":"210"},"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/T10028","display_name":"Topic Modeling","score":0.9995999932289124,"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/T13083","display_name":"Advanced Text Analysis 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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8549254536628723},{"id":"https://openalex.org/keywords/agglutinative-language","display_name":"Agglutinative language","score":0.7642464637756348},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.7019527554512024},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6591722965240479},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.6332076191902161},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5901985168457031},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.5890737771987915},{"id":"https://openalex.org/keywords/text-segmentation","display_name":"Text segmentation","score":0.5105549097061157},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.5066633820533752},{"id":"https://openalex.org/keywords/turkish","display_name":"Turkish","score":0.5041509866714478},{"id":"https://openalex.org/keywords/noun","display_name":"Noun","score":0.44720685482025146},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.42656394839286804},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.34948158264160156},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.1968030035495758},{"id":"https://openalex.org/keywords/parsing","display_name":"Parsing","score":0.19341862201690674}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8549254536628723},{"id":"https://openalex.org/C80875076","wikidata":"https://www.wikidata.org/wiki/Q171263","display_name":"Agglutinative language","level":3,"score":0.7642464637756348},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.7019527554512024},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6591722965240479},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.6332076191902161},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5901985168457031},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5890737771987915},{"id":"https://openalex.org/C98501671","wikidata":"https://www.wikidata.org/wiki/Q1948408","display_name":"Text segmentation","level":3,"score":0.5105549097061157},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.5066633820533752},{"id":"https://openalex.org/C2781121862","wikidata":"https://www.wikidata.org/wiki/Q256","display_name":"Turkish","level":2,"score":0.5041509866714478},{"id":"https://openalex.org/C121934690","wikidata":"https://www.wikidata.org/wiki/Q1084","display_name":"Noun","level":2,"score":0.44720685482025146},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.42656394839286804},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.34948158264160156},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.1968030035495758},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.19341862201690674},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","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/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0}],"mesh":[],"locations_count":6,"locations":[{"id":"doi:10.1017/s135132490200284x","is_oa":false,"landing_page_url":"https://doi.org/10.1017/s135132490200284x","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:CiteSeerX.psu:10.1.1.11.6127","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.11.6127","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://ranger.uta.edu/~alp/ix/readings/IEfromTurkish.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.15.2068","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.15.2068","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.research.att.com/~gtur/pubs/Phd.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.25.4241","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.25.4241","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.research.att.com/~gtur/Phd.ps","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.58.3550","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.58.3550","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.research.att.com/~dtur/pubs/NLE03.pdf","raw_type":"text"},{"id":"pmh:oai:repository.bilkent.edu.tr:11693/18581","is_oa":true,"landing_page_url":"http://hdl.handle.net/11693/18581","pdf_url":null,"source":{"id":"https://openalex.org/S4306400079","display_name":"Bilkent University Institutional Repository (Bilkent University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I168864056","host_organization_name":"Bilkent University","host_organization_lineage":["https://openalex.org/I168864056"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Thesis"}],"best_oa_location":{"id":"pmh:oai:repository.bilkent.edu.tr:11693/18581","is_oa":true,"landing_page_url":"http://hdl.handle.net/11693/18581","pdf_url":null,"source":{"id":"https://openalex.org/S4306400079","display_name":"Bilkent University Institutional Repository (Bilkent University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I168864056","host_organization_name":"Bilkent University","host_organization_lineage":["https://openalex.org/I168864056"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Thesis"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.8100000023841858}],"awards":[],"funders":[{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W61566120","https://openalex.org/W1490831147","https://openalex.org/W1520377376","https://openalex.org/W1557074680","https://openalex.org/W1614151208","https://openalex.org/W1991846425","https://openalex.org/W2003676127","https://openalex.org/W2004316800","https://openalex.org/W2018560257","https://openalex.org/W2061271742","https://openalex.org/W2062289558","https://openalex.org/W2068882115","https://openalex.org/W2097333193","https://openalex.org/W2135909747","https://openalex.org/W2140836433","https://openalex.org/W2149041454","https://openalex.org/W2157439354","https://openalex.org/W2167055684","https://openalex.org/W2426479676","https://openalex.org/W2787077853","https://openalex.org/W3034491700"],"related_works":["https://openalex.org/W2098104139","https://openalex.org/W4290739335","https://openalex.org/W4290735204","https://openalex.org/W3217723215","https://openalex.org/W2114358883","https://openalex.org/W2129812225","https://openalex.org/W4291015379","https://openalex.org/W2029306354","https://openalex.org/W1745277","https://openalex.org/W2144748275"],"abstract_inverted_index":{"This":[0,201],"paper":[1],"presents":[2],"the":[3,61,65,70,86,90,100,120,125,131,136,146,151,155,162,175,179,195,206,229,233,238,242,253,257,263,274,283,293],"results":[4,279],"of":[5,30,64,69,89,124,154,161,178,232,256,270,292],"a":[6,26,35,296,302],"study":[7],"on":[8,189,228],"information":[9,104,217,224,309],"extraction":[10,310],"from":[11],"unrestricted":[12],"Turkish":[13,42],"text":[14],"using":[15,60,98,149,174,286],"statistical":[16,55,96,303],"language":[17],"processing":[18],"methods.":[19],"In":[20,74],"languages":[21,40],"like":[22,41],"English,":[23],"there":[24],"is":[25,50,142,202,226],"very":[27,44],"small":[28],"number":[29],"possible":[31],"word":[32],"forms":[33,63,153,177,231],"with":[34,130,241],"given":[36],"root":[37],"word.":[38],"However,":[39],"have":[43,93,118,166,183],"productive":[45],"agglutinative":[46],"morphology.":[47],"Thus,":[48],"it":[49,129],"an":[51,268],"issue":[52],"to":[53,76,105,139,169,194,219,273,300],"build":[54],"models":[56],"for":[57,312],"specific":[58],"tasks":[59,311],"surface":[62,152,176,230],"words,":[66,258,294],"mainly":[67],"because":[68],"data":[71],"sparseness":[72],"problem.":[73],"order":[75],"alleviate":[77],"this":[78],"problem,":[79],"we":[80,117,182,213,236,251,261],"used":[81,214],"additional":[82],"syntactic":[83],"information,":[84,288],"i.e.":[85,289],"morphological":[87,103,254,290],"structure":[88],"words.":[91,156,234],"We":[92],"successfully":[94],"applied":[95],"methods":[97],"both":[99],"lexical":[101,132,243],"and":[102,110,127,134,181,245,259,266,295],"sentence":[106,115],"segmentation,":[107,109,116,159],"topic":[108,158],"name":[111,211],"tagging":[112],"tasks.":[113],"For":[114,157,210],"modeled":[119,252,262],"final":[121],"inflectional":[122],"groups":[123],"words":[126,163,180],"combined":[128,237],"model,":[133,244],"decreased":[135],"error":[137,187],"rate":[138,188],"4.34%,":[140],"which":[141],"21%":[143],"better":[144,204],"than":[145,173,205],"result":[147],"obtained":[148,246],"only":[150],"stems":[160],"(especially":[164],"nouns)":[165],"been":[167],"found":[168],"be":[170],"more":[171],"effective":[172],"achieved":[184],"10.90%":[185],"segmentation":[186,198],"our":[190],"test":[191],"set":[192],"according":[193,272],"weighted":[196],"TDT-2":[197],"cost":[199],"metric.":[200],"32%":[203],"word-based":[207],"baseline":[208],"model.":[209],"tagging,":[212],"four":[215],"different":[216],"sources":[218],"model":[220,304],"names.":[221],"Our":[222,278],"first":[223],"source":[225],"based":[227],"Then":[235],"contextual":[239],"cues":[240],"some":[247],"improvement.":[248],"After":[249],"this,":[250],"analyses":[255,291],"finally":[260],"tag":[264],"sequence,":[265],"reached":[267],"F-Measure":[269],"91.56%,":[271],"MUC":[275],"evaluation":[276],"criteria.":[277],"are":[280],"important":[281],"in":[282],"sense":[284],"that,":[285],"linguistic":[287],"corpus":[297],"large":[298],"enough":[299],"train":[301],"significantly":[305],"improves":[306],"these":[307],"basic":[308],"Turkish.":[313]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":12},{"year":2020,"cited_by_count":8},{"year":2019,"cited_by_count":6},{"year":2018,"cited_by_count":9},{"year":2017,"cited_by_count":11},{"year":2016,"cited_by_count":6},{"year":2015,"cited_by_count":7},{"year":2014,"cited_by_count":8},{"year":2013,"cited_by_count":3},{"year":2012,"cited_by_count":3}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}