{"id":"https://openalex.org/W2078349113","doi":"https://doi.org/10.1109/tasl.2011.2162323","title":"Discriminative Language Modeling with Linguistic and Statistically Derived Features","display_name":"Discriminative Language Modeling with Linguistic and Statistically Derived Features","publication_year":2011,"publication_date":"2011-01-01","ids":{"openalex":"https://openalex.org/W2078349113","doi":"https://doi.org/10.1109/tasl.2011.2162323","mag":"2078349113"},"language":"en","primary_location":{"id":"doi:10.1109/tasl.2011.2162323","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tasl.2011.2162323","pdf_url":null,"source":{"id":"https://openalex.org/S199497470","display_name":"IEEE Transactions on Audio Speech and Language Processing","issn_l":"1558-7916","issn":["1558-7916","1558-7924"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Audio, Speech, and Language Processing","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/A5032284977","display_name":"Ebru Ar\u0131soy","orcid":null},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]},{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"E. Arisoy","raw_affiliation_strings":["Speech Technologies for Media and ACCES Department, IBM Thomas J. Watson Research Center, Yorktown Heights, NY, USA","ACCES Dept., IBM T. J. Watson Res. Center, Yorktown Heights, NY, USA#TAB#"],"affiliations":[{"raw_affiliation_string":"Speech Technologies for Media and ACCES Department, IBM Thomas J. Watson Research Center, Yorktown Heights, NY, USA","institution_ids":["https://openalex.org/I4210114115"]},{"raw_affiliation_string":"ACCES Dept., IBM T. J. Watson Res. Center, Yorktown Heights, NY, USA#TAB#","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055086464","display_name":"Murat Sara\u00e7lar","orcid":"https://orcid.org/0000-0002-7435-8510"},"institutions":[{"id":"https://openalex.org/I4405392","display_name":"Bo\u011fazi\u00e7i University","ror":"https://ror.org/03z9tma90","country_code":"TR","type":"education","lineage":["https://openalex.org/I4405392"]}],"countries":["TR"],"is_corresponding":false,"raw_author_name":"M. Saraclar","raw_affiliation_strings":["Electrical and Electronics Engineering Department, Bo\u011fazi\u00e7i University, Bebek, Istanbul, Turkey","Electr. & Electron. Eng. Dept., Bogazici Univ., Istanbul, Turkey"],"affiliations":[{"raw_affiliation_string":"Electrical and Electronics Engineering Department, Bo\u011fazi\u00e7i University, Bebek, Istanbul, Turkey","institution_ids":["https://openalex.org/I4405392"]},{"raw_affiliation_string":"Electr. & Electron. Eng. Dept., Bogazici Univ., Istanbul, Turkey","institution_ids":["https://openalex.org/I4405392"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020068498","display_name":"Brian Roark","orcid":null},"institutions":[{"id":"https://openalex.org/I165690674","display_name":"Oregon Health & Science University","ror":"https://ror.org/009avj582","country_code":"US","type":"education","lineage":["https://openalex.org/I165690674"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"B. Roark","raw_affiliation_strings":["Center of Spoken Language Understanding, Oregon Health and Science University, Beaverton, OR, USA","Center for Spoken Language Understanding, Oregon Health & Sci. Univ., Beaverton, OR, USA"],"affiliations":[{"raw_affiliation_string":"Center of Spoken Language Understanding, Oregon Health and Science University, Beaverton, OR, USA","institution_ids":["https://openalex.org/I165690674"]},{"raw_affiliation_string":"Center for Spoken Language Understanding, Oregon Health & Sci. Univ., Beaverton, OR, USA","institution_ids":["https://openalex.org/I165690674"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5025419994","display_name":"Izhak Shafran","orcid":null},"institutions":[{"id":"https://openalex.org/I165690674","display_name":"Oregon Health & Science University","ror":"https://ror.org/009avj582","country_code":"US","type":"education","lineage":["https://openalex.org/I165690674"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"I. Shafran","raw_affiliation_strings":["Center of Spoken Language Understanding, Oregon Health and Science University, Beaverton, OR, USA","Center for Spoken Language Understanding, Oregon Health & Sci. Univ., Beaverton, OR, USA"],"affiliations":[{"raw_affiliation_string":"Center of Spoken Language Understanding, Oregon Health and Science University, Beaverton, OR, USA","institution_ids":["https://openalex.org/I165690674"]},{"raw_affiliation_string":"Center for Spoken Language Understanding, Oregon Health & Sci. Univ., Beaverton, OR, USA","institution_ids":["https://openalex.org/I165690674"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5032284977"],"corresponding_institution_ids":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"],"apc_list":null,"apc_paid":null,"fwci":5.1309,"has_fulltext":false,"cited_by_count":23,"citation_normalized_percentile":{"value":0.95359501,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"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/T10201","display_name":"Speech Recognition and Synthesis","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/T10028","display_name":"Topic Modeling","score":0.9990000128746033,"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":0.7250947952270508},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.693695068359375},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6253764033317566},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.5996811389923096},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.5588797926902771},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5361219644546509},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5182502269744873},{"id":"https://openalex.org/keywords/agglutinative-language","display_name":"Agglutinative language","score":0.43168407678604126},{"id":"https://openalex.org/keywords/rank","display_name":"Rank (graph theory)","score":0.43158698081970215},{"id":"https://openalex.org/keywords/notation","display_name":"Notation","score":0.42472630739212036},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.3841858208179474},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.15322992205619812},{"id":"https://openalex.org/keywords/morpheme","display_name":"Morpheme","score":0.1270972490310669}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7250947952270508},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.693695068359375},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6253764033317566},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.5996811389923096},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.5588797926902771},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5361219644546509},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5182502269744873},{"id":"https://openalex.org/C80875076","wikidata":"https://www.wikidata.org/wiki/Q171263","display_name":"Agglutinative language","level":3,"score":0.43168407678604126},{"id":"https://openalex.org/C164226766","wikidata":"https://www.wikidata.org/wiki/Q7293202","display_name":"Rank (graph theory)","level":2,"score":0.43158698081970215},{"id":"https://openalex.org/C45357846","wikidata":"https://www.wikidata.org/wiki/Q2001982","display_name":"Notation","level":2,"score":0.42472630739212036},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.3841858208179474},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.15322992205619812},{"id":"https://openalex.org/C165297611","wikidata":"https://www.wikidata.org/wiki/Q43249","display_name":"Morpheme","level":2,"score":0.1270972490310669},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tasl.2011.2162323","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tasl.2011.2162323","pdf_url":null,"source":{"id":"https://openalex.org/S199497470","display_name":"IEEE Transactions on Audio Speech and Language Processing","issn_l":"1558-7916","issn":["1558-7916","1558-7924"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7300000190734863,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":55,"referenced_works":["https://openalex.org/W813000","https://openalex.org/W75895223","https://openalex.org/W129940430","https://openalex.org/W153434986","https://openalex.org/W274041255","https://openalex.org/W1494693235","https://openalex.org/W1516736046","https://openalex.org/W1574901103","https://openalex.org/W1590952807","https://openalex.org/W1631260214","https://openalex.org/W1828401780","https://openalex.org/W1915022094","https://openalex.org/W1984635093","https://openalex.org/W1989705153","https://openalex.org/W1997346563","https://openalex.org/W2004316800","https://openalex.org/W2005076803","https://openalex.org/W2008652694","https://openalex.org/W2010797893","https://openalex.org/W2031287088","https://openalex.org/W2032942114","https://openalex.org/W2050938027","https://openalex.org/W2052131621","https://openalex.org/W2056250865","https://openalex.org/W2062323476","https://openalex.org/W2069712814","https://openalex.org/W2079152520","https://openalex.org/W2093525792","https://openalex.org/W2112302671","https://openalex.org/W2114858359","https://openalex.org/W2121127625","https://openalex.org/W2121227244","https://openalex.org/W2123893795","https://openalex.org/W2125712079","https://openalex.org/W2128201184","https://openalex.org/W2129812225","https://openalex.org/W2132502917","https://openalex.org/W2136727248","https://openalex.org/W2142506199","https://openalex.org/W2149980590","https://openalex.org/W2152753389","https://openalex.org/W2158025800","https://openalex.org/W2158148237","https://openalex.org/W2158297186","https://openalex.org/W2172045870","https://openalex.org/W2902905787","https://openalex.org/W2998864486","https://openalex.org/W3183153947","https://openalex.org/W4251925141","https://openalex.org/W4285719527","https://openalex.org/W6603131336","https://openalex.org/W6638575021","https://openalex.org/W6640118610","https://openalex.org/W6651845459","https://openalex.org/W6678277124"],"related_works":["https://openalex.org/W2728343294","https://openalex.org/W2952149385","https://openalex.org/W1531783358","https://openalex.org/W2113687551","https://openalex.org/W2112752961","https://openalex.org/W1831014557","https://openalex.org/W2129812225","https://openalex.org/W1745277","https://openalex.org/W2050938027","https://openalex.org/W2914864687"],"abstract_inverted_index":{"This":[0],"paper":[1,114],"focuses":[2],"on":[3],"integrating":[4],"linguistically":[5],"motivated":[6],"and":[7,63,104,110,135,196,208],"statistically":[8],"derived":[9],"information":[10,50,100,119,170,189],"into":[11,147],"language":[12,17,33,137,143,148],"modeling.":[13,149],"We":[14,127,150],"use":[15,183],"discriminative":[16],"models":[18,34],"(DLMs)":[19],"as":[20,53,176,178],"a":[21,88],"complementary":[22],"approach":[23],"to":[24,35,65,86,116,131,154,186,219],"the":[25,67,77,121,160],"conventional":[26],"<formula":[27,68],"formulatype=\"inline\"":[28,69],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[29,70],"xmlns:xlink=\"http://www.w3.org/1999/xlink\"><tex":[30,71],"Notation=\"TeX\">$n$</tex></formula>":[31],"-gram":[32],"benefit":[36],"from":[37,171,190],"discriminatively":[38,58],"trained":[39,59],"parameter":[40],"estimates":[41],"for":[42,221],"overlapping":[43],"features.":[44,54,126],"In":[45,84],"our":[46,155,205],"DLM":[47,220],"approach,":[48],"relevant":[49],"is":[51,162,174],"encoded":[52],"Feature":[55],"weights":[56],"are":[57],"using":[60,107],"training":[61],"examples":[62],"used":[64],"re-rank":[66],"Notation=\"TeX\">$N$</tex>":[72],"</formula>":[73],"-best":[74],"hypotheses":[75,173],"of":[76,92,123,139,164],"baseline":[78,206],"automatic":[79],"speech":[80],"recognition":[81],"(ASR)":[82],"system.":[83],"addition":[85],"presenting":[87],"more":[89],"complete":[90],"picture":[91],"previously":[93],"proposed":[94],"feature":[95],"sets":[96],"that":[97],"extract":[98],"implicit":[99,168],"available":[101],"at":[102],"lexical":[103],"sub-lexical":[105,165,172,191],"levels":[106],"both":[108],"linguistic":[109,129,169,195],"statistical":[111,184,197],"approaches,":[112],"this":[113],"attempts":[115],"incorporate":[117,132],"semantic":[118],"in":[120],"form":[122],"topic":[124],"sensitive":[125],"explore":[128],"features":[130,198,214],"complex":[133],"morphological":[134],"syntactic":[136],"characteristics":[138],"Turkish,":[140],"an":[141],"agglutinative":[142],"with":[144,194],"rich":[145],"morphology,":[146],"also":[151],"apply":[152],"DLMs":[153,193],"sub-lexical-based":[156],"ASR":[157,210],"system":[158],"where":[159],"vocabulary":[161],"composed":[163],"units.":[166,192],"Obtaining":[167],"not":[175],"straightforward":[177],"word":[179],"hypotheses,":[180],"so":[181],"we":[182],"methods":[185],"derive":[187],"useful":[188],"yield":[199],"significant,":[200],"0.8%\u20131.1%":[201],"absolute,":[202],"improvements":[203],"over":[204],"word-based":[207],"sub-word-based":[209],"systems.":[211],"The":[212],"explored":[213],"can":[215],"be":[216],"easily":[217],"extended":[218],"other":[222],"languages":[223],".":[224]},"counts_by_year":[{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":4},{"year":2012,"cited_by_count":7}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}