{"id":"https://openalex.org/W1992196410","doi":"https://doi.org/10.1109/tasl.2012.2183870","title":"Topic-Dependent-Class-Based $n$-Gram Language Model","display_name":"Topic-Dependent-Class-Based $n$-Gram Language Model","publication_year":2012,"publication_date":"2012-01-11","ids":{"openalex":"https://openalex.org/W1992196410","doi":"https://doi.org/10.1109/tasl.2012.2183870","mag":"1992196410"},"language":"en","primary_location":{"id":"doi:10.1109/tasl.2012.2183870","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tasl.2012.2183870","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/A5067201583","display_name":"Welly Naptali","orcid":null},"institutions":[{"id":"https://openalex.org/I22299242","display_name":"Kyoto University","ror":"https://ror.org/02kpeqv85","country_code":"JP","type":"education","lineage":["https://openalex.org/I22299242"]},{"id":"https://openalex.org/I39012071","display_name":"Kyoto College of Graduate Studies for Informatics","ror":"https://ror.org/05mzj8a56","country_code":"JP","type":"education","lineage":["https://openalex.org/I39012071"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Welly Naptali","raw_affiliation_strings":["Academic Center for Computing and Media Studies, Kyoto University, Kyoto, Japan","[Acad. Center for Comput. & Media Studies, Kyoto Univ., Kyoto, Japan]"],"affiliations":[{"raw_affiliation_string":"Academic Center for Computing and Media Studies, Kyoto University, Kyoto, Japan","institution_ids":["https://openalex.org/I39012071","https://openalex.org/I22299242"]},{"raw_affiliation_string":"[Acad. Center for Comput. & Media Studies, Kyoto Univ., Kyoto, Japan]","institution_ids":["https://openalex.org/I22299242"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047336359","display_name":"Masatoshi Tsuchiya","orcid":"https://orcid.org/0000-0003-1862-8149"},"institutions":[{"id":"https://openalex.org/I136259955","display_name":"Toyohashi University of Technology","ror":"https://ror.org/04ezg6d83","country_code":"JP","type":"education","lineage":["https://openalex.org/I136259955"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Masatoshi Tsuchiya","raw_affiliation_strings":["Department of Information and Multimedia Center, Toyohashi University of Technology, Toyohashi, Japan","Dept. of Inf. & Multimedia Center, Toyohashi Univ. of Technol., Toyohashi, Japan"],"affiliations":[{"raw_affiliation_string":"Department of Information and Multimedia Center, Toyohashi University of Technology, Toyohashi, Japan","institution_ids":["https://openalex.org/I136259955"]},{"raw_affiliation_string":"Dept. of Inf. & Multimedia Center, Toyohashi Univ. of Technol., Toyohashi, Japan","institution_ids":["https://openalex.org/I136259955"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5018428974","display_name":"Seiichi Nakagawa","orcid":"https://orcid.org/0000-0002-6533-5536"},"institutions":[{"id":"https://openalex.org/I136259955","display_name":"Toyohashi University of Technology","ror":"https://ror.org/04ezg6d83","country_code":"JP","type":"education","lineage":["https://openalex.org/I136259955"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Seiichi Nakagawa","raw_affiliation_strings":["Department of Computer Science and Engineering, Toyohashi University of Technology, Toyohashi, Japan","[Dept. of Computer Science and Engineering, Toyohashi University of Technology, Toyohashi, Japan]"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Toyohashi University of Technology, Toyohashi, Japan","institution_ids":["https://openalex.org/I136259955"]},{"raw_affiliation_string":"[Dept. of Computer Science and Engineering, Toyohashi University of Technology, Toyohashi, Japan]","institution_ids":["https://openalex.org/I136259955"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5067201583"],"corresponding_institution_ids":["https://openalex.org/I22299242","https://openalex.org/I39012071"],"apc_list":null,"apc_paid":null,"fwci":4.2813,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.9400976,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"20","issue":"5","first_page":"1513","last_page":"1525"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","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/T10028","display_name":"Topic Modeling","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/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":0.9976000189781189,"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/perplexity","display_name":"Perplexity","score":0.7364277839660645},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6682883501052856},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6174089908599854},{"id":"https://openalex.org/keywords/latent-dirichlet-allocation","display_name":"Latent Dirichlet allocation","score":0.6136248111724854},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5881519317626953},{"id":"https://openalex.org/keywords/noun","display_name":"Noun","score":0.5762227177619934},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.48212599754333496},{"id":"https://openalex.org/keywords/voting","display_name":"Voting","score":0.4797407388687134},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.45092010498046875},{"id":"https://openalex.org/keywords/bipartite-graph","display_name":"Bipartite graph","score":0.4350188374519348},{"id":"https://openalex.org/keywords/topic-model","display_name":"Topic model","score":0.356278657913208},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.13188469409942627}],"concepts":[{"id":"https://openalex.org/C100279451","wikidata":"https://www.wikidata.org/wiki/Q372193","display_name":"Perplexity","level":3,"score":0.7364277839660645},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6682883501052856},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6174089908599854},{"id":"https://openalex.org/C500882744","wikidata":"https://www.wikidata.org/wiki/Q269236","display_name":"Latent Dirichlet allocation","level":3,"score":0.6136248111724854},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5881519317626953},{"id":"https://openalex.org/C121934690","wikidata":"https://www.wikidata.org/wiki/Q1084","display_name":"Noun","level":2,"score":0.5762227177619934},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.48212599754333496},{"id":"https://openalex.org/C520049643","wikidata":"https://www.wikidata.org/wiki/Q189760","display_name":"Voting","level":3,"score":0.4797407388687134},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.45092010498046875},{"id":"https://openalex.org/C197657726","wikidata":"https://www.wikidata.org/wiki/Q174733","display_name":"Bipartite graph","level":3,"score":0.4350188374519348},{"id":"https://openalex.org/C171686336","wikidata":"https://www.wikidata.org/wiki/Q3532085","display_name":"Topic model","level":2,"score":0.356278657913208},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.13188469409942627},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tasl.2012.2183870","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tasl.2012.2183870","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":0.8500000238418579,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":51,"referenced_works":["https://openalex.org/W21664255","https://openalex.org/W65340009","https://openalex.org/W113724690","https://openalex.org/W182840523","https://openalex.org/W1509106210","https://openalex.org/W1516580204","https://openalex.org/W1549285799","https://openalex.org/W1573514622","https://openalex.org/W1574845294","https://openalex.org/W1597533204","https://openalex.org/W1644652583","https://openalex.org/W1660390307","https://openalex.org/W1665921526","https://openalex.org/W1880262756","https://openalex.org/W1974515274","https://openalex.org/W2009450594","https://openalex.org/W2018844855","https://openalex.org/W2020073413","https://openalex.org/W2031284124","https://openalex.org/W2056492762","https://openalex.org/W2071315630","https://openalex.org/W2080213370","https://openalex.org/W2081295016","https://openalex.org/W2084084380","https://openalex.org/W2096610504","https://openalex.org/W2110027950","https://openalex.org/W2110711961","https://openalex.org/W2112874453","https://openalex.org/W2112958284","https://openalex.org/W2127836646","https://openalex.org/W2130696866","https://openalex.org/W2132575437","https://openalex.org/W2134939182","https://openalex.org/W2147766635","https://openalex.org/W2151315616","https://openalex.org/W2159382562","https://openalex.org/W2159518412","https://openalex.org/W2217717732","https://openalex.org/W2401075988","https://openalex.org/W2502991127","https://openalex.org/W4237791300","https://openalex.org/W6604570268","https://openalex.org/W6630946131","https://openalex.org/W6632753169","https://openalex.org/W6634065907","https://openalex.org/W6635726886","https://openalex.org/W6652330410","https://openalex.org/W6677270348","https://openalex.org/W6679505441","https://openalex.org/W6688437984","https://openalex.org/W6713120608"],"related_works":["https://openalex.org/W2043781532","https://openalex.org/W4293734197","https://openalex.org/W2890727200","https://openalex.org/W2132551194","https://openalex.org/W2114062410","https://openalex.org/W2250993361","https://openalex.org/W2131689821","https://openalex.org/W2147766635","https://openalex.org/W142374489","https://openalex.org/W2808739814"],"abstract_inverted_index":{"A":[0,29],"topic-dependent-class":[1],"(TDC)-based":[2],"<i":[3,102,114,166],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[4,103,115,167],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">n</i>":[5,104,116,168],"-gram":[6,105],"language":[7,65],"model":[8,66],"(LM)":[9],"is":[10,36,130,252,275],"a":[11,16,32,98,110,121,131,182],"topic-based":[12],"LM":[13,106,184,193,242],"that":[14,87,239],"employs":[15],"semantic":[17],"extraction":[18],"method":[19],"to":[20,254,278,285,291],"reveal":[21],"latent":[22],"topic":[23,30],"information":[24],"extracted":[25],"from":[26],"noun-noun":[27],"relations.":[28],"of":[31,41,90,134,163,197,207,216],"given":[33],"word":[34,209],"sequence":[35],"decided":[37],"on":[38,69,226,257,264],"the":[39,49,164,171,189,198,208,217,227,232,240,247,258,265,269,273,279,286,292],"basis":[40],"most":[42],"frequently":[43],"occuring":[44],"(weighted)":[45],"noun":[46,70],"classes":[47],"in":[48,88,170,205,272],"context":[50],"history":[51],"through":[52,185],"voting.":[53],"Our":[54],"previous":[55,136],"work":[56,137],"(W.":[57],"Naptali,":[58],"M.":[59],"Tsuchiya,":[60],"and":[61,107,120,138,159,191,213,231,246,261,282],"S.":[62],"Seiichi,":[63],"\u201cTopic-dependent":[64],"with":[67],"voting":[68],"history,\u201dACM":[71],"Trans.":[72],"Asian":[73],"Language":[74],"Information":[75],"Processing":[76],"(TALIP),":[77],"vol.":[78],"9,":[79],"no.":[80],"2,":[81],"pp.":[82],"1-31,":[83],"2010)":[84],"has":[85],"shown":[86],"terms":[89,206],"perplexity,":[91],"TDCs":[92,147,161],"outperform":[93],"several":[94],"state-of-the-art":[95],"baselines,":[96],"i.e.,":[97],"word-based":[99,165],"or":[100],"class-based":[101],"their":[108],"interpolation,":[109],"cache-based":[111,183,192],"LM,":[112,119],"an":[113,203,214],"-gram-based":[117],"topic-dependent":[118,126],"Latent":[122],"Dirichlet":[123],"Allocation":[124],"(LDA)-based":[125],"LM.":[127],"This":[128],"study":[129],"follow":[132],"up":[133,253],"our":[135],"there":[139],"are":[140],"three":[141],"key":[142],"differences.":[143],"First,":[144],"we":[145,180,201],"improve":[146],"by":[148],"employing":[149],"soft-clustering":[150],"and/or":[151,173],"soft-voting":[152],"techniques,":[153],"which":[154],"solve":[155],"data":[156],"shrinking":[157],"problems":[158],"make":[160],"independent":[162],"-gram,":[169],"training":[172],"test":[174],"phases.":[175],"Second,":[176],"for":[177],"further":[178],"improvement,":[179],"incorporate":[181],"unigram":[186],"scaling,":[187],"because":[188],"TDC":[190,241],"capture":[194],"different":[195],"properties":[196],"language.":[199],"Finally,":[200],"provide":[202],"evaluation":[204],"error":[210],"rate":[211],"(WER)":[212],"analysis":[215],"automatic":[218],"speech":[219],"recognition":[220],"(ASR)":[221],"rescoring":[222],"task.":[223],"Experiments":[224],"performed":[225],"Wall":[228],"Street":[229],"Journal":[230],"Mainichi":[233],"Shimbun":[234],"(a":[235],"Japanese":[236,266,287],"newspaper)":[237],"demonstrate":[238],"improves":[243],"both":[244],"perplexity":[245,250],"WER.":[248],"The":[249],"reduction":[251,271],"25.1%":[255],"relative":[256,263,277,284],"English":[259,280],"corpus":[260],"25.7%":[262],"corpus.":[267],"Furthermore,":[268],"greatest":[270],"WER":[274],"15.2%":[276],"ASR":[281],"24.3":[283],"ASR,":[288],"as":[289],"compared":[290],"baseline.":[293]},"counts_by_year":[{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":7},{"year":2013,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}