{"id":"https://openalex.org/W20608663","doi":"https://doi.org/10.21437/interspeech.2004-355","title":"N-gram language modeling of Japanese using bunsetsu boundaries","display_name":"N-gram language modeling of Japanese using bunsetsu boundaries","publication_year":2004,"publication_date":"2004-10-04","ids":{"openalex":"https://openalex.org/W20608663","doi":"https://doi.org/10.21437/interspeech.2004-355","mag":"20608663"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2004-355","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2004-355","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2004","raw_type":"proceedings-article"},"type":"conference-paper","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/A5113619694","display_name":"Sungyup Chung","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sungyup Chung","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108197272","display_name":"Keikichi Hirose","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Keikichi Hirose","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5041213266","display_name":"Nobuaki Minematsu","orcid":"https://orcid.org/0000-0002-8778-9555"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Nobuaki Minematsu","raw_affiliation_strings":["university of Tokyo;"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"university of Tokyo;","institution_ids":["https://openalex.org/I74801974"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"993","last_page":"996"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9980000257492065,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9980000257492065,"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":0.9975000023841858,"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":0.9933000206947327,"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":0.8576923608779907},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7779338359832764},{"id":"https://openalex.org/keywords/phrase","display_name":"Phrase","score":0.7313582897186279},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.7148565053939819},{"id":"https://openalex.org/keywords/n-gram","display_name":"n-gram","score":0.6677456498146057},{"id":"https://openalex.org/keywords/pronunciation","display_name":"Pronunciation","score":0.6438711285591125},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6333154439926147},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6165323257446289},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5448108315467834},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5193639397621155},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.4909875690937042},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.485477477312088},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.4724683463573456},{"id":"https://openalex.org/keywords/parsing","display_name":"Parsing","score":0.46697092056274414},{"id":"https://openalex.org/keywords/stress","display_name":"Stress (linguistics)","score":0.4439888596534729},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.2585102319717407}],"concepts":[{"id":"https://openalex.org/C100279451","wikidata":"https://www.wikidata.org/wiki/Q372193","display_name":"Perplexity","level":3,"score":0.8576923608779907},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7779338359832764},{"id":"https://openalex.org/C2776224158","wikidata":"https://www.wikidata.org/wiki/Q187931","display_name":"Phrase","level":2,"score":0.7313582897186279},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.7148565053939819},{"id":"https://openalex.org/C117884012","wikidata":"https://www.wikidata.org/wiki/Q94489","display_name":"n-gram","level":3,"score":0.6677456498146057},{"id":"https://openalex.org/C2780844864","wikidata":"https://www.wikidata.org/wiki/Q184377","display_name":"Pronunciation","level":2,"score":0.6438711285591125},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6333154439926147},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6165323257446289},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5448108315467834},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5193639397621155},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.4909875690937042},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.485477477312088},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.4724683463573456},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.46697092056274414},{"id":"https://openalex.org/C2776756274","wikidata":"https://www.wikidata.org/wiki/Q181767","display_name":"Stress (linguistics)","level":2,"score":0.4439888596534729},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.2585102319717407},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2004-355","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2004-355","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2004","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.587.6496","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.587.6496","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.gavo.t.u-tokyo.ac.jp/~mine/paper/PDF/2004/ICSLP_p993-996_t2004-10.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.800000011920929,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":4,"referenced_works":["https://openalex.org/W1590070522","https://openalex.org/W1600591519","https://openalex.org/W1939938582","https://openalex.org/W1996903695"],"related_works":["https://openalex.org/W2252095989","https://openalex.org/W4322096525","https://openalex.org/W2787311093","https://openalex.org/W2132221452","https://openalex.org/W2105076537","https://openalex.org/W1577263324","https://openalex.org/W2169518243","https://openalex.org/W2050138804","https://openalex.org/W2151348424","https://openalex.org/W1494910745"],"abstract_inverted_index":{"A":[0,38],"new":[1],"scheme":[2,40,164],"of":[3,36,46,70,124,134,151,160,211],"N-gram":[4,125],"language":[5,181],"modeling":[6,126,176,182],"was":[7,99,108,155,183,200,207],"pro-posed":[8],"for":[9,17,157],"Japanese,":[10],"where":[11],"word":[12,197],"N-grams":[13],"were":[14],"calculated":[15],"separately":[16],"the":[18,54,64,102,115,122,144,158,162,167,174,204],"two":[19,132],"cases:":[20],"crossing":[21,24,139],"and":[22,127,137,190],"not":[23,138],"bunsetsu":[25,28,112,140],"boundaries.":[26],"Here,":[27],"is":[29],"a":[30,57,75,87,91,96,105,186],"basic":[31],"gram-matical":[32],"(and":[33],"pronunciation)":[34],"unit":[35],"Japanese.":[37],"similar":[39],"using":[41,95],"accent":[42,71],"phrase":[43,72],"boundaries":[44,48,73,81,113],"instead":[45],"bun-setsu":[47,80],"has":[49],"already":[50],"been":[51],"proposed":[52,163,180],"by":[53,110,128,169],"au-thors":[55],"with":[56,90],"certain":[58],"success,":[59],"but":[60],"it":[61,191],"suffered":[62],"from":[63,86,101,114,131,173],"train-ing":[65],"data":[66],"shortage,":[67],"because":[68],"assignment":[69],"requires":[74],"speech":[76,188],"corpus.":[77],"In":[78],"contrast,":[79],"can":[82],"be":[83],"detected":[84],"automatically":[85],"written":[88],"text":[89],"rather":[92],"high":[93],"accuracy":[94],"parser.":[97],"It":[98],"shown":[100],"experiment":[103],"that":[104,193],"perplexity":[106],"re-duction":[107],"possible":[109],"estimating":[111],"history":[116],"longer":[117],"than":[118],"N-1":[119],"words":[120],"in":[121,196],"case":[123],"selecting":[129],"one":[130],"types":[133],"models":[135],"(crossing":[136],"bound-aries)":[141],"according":[142],"to":[143,185],"estimation.":[145],"When":[146],"1":[147],"or":[148],"3":[149],"years":[150],"Mainichi":[152],"Newspaper":[153],"corpus":[154,206],"used":[156],"training":[159,205],"tri-grams,":[161],"could":[165],"reduce":[166],"perplex-ity":[168],"around":[170],"8":[171],"%":[172],"baseline":[175],"(without":[177],"separation).":[178],"The":[179],"ap-plied":[184],"continuous":[187],"recognition,":[189],"showed":[192],"an":[194],"improvement":[195],"recognition":[198],"rate":[199],"possi-ble":[201],"especially":[202],"when":[203],"small":[208],"(1":[209],"year":[210],"newspaper).":[212],"1.":[213]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}