{"id":"https://openalex.org/W2134591869","doi":"https://doi.org/10.1109/iscslp.2012.6423548","title":"Collecting sentences from web resources for constructing spontaneous Chinese language model","display_name":"Collecting sentences from web resources for constructing spontaneous Chinese language model","publication_year":2012,"publication_date":"2012-12-01","ids":{"openalex":"https://openalex.org/W2134591869","doi":"https://doi.org/10.1109/iscslp.2012.6423548","mag":"2134591869"},"language":"en","primary_location":{"id":"doi:10.1109/iscslp.2012.6423548","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp.2012.6423548","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 8th International Symposium on Chinese Spoken Language Processing","raw_type":"proceedings-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/A5041446566","display_name":"Xinhui Hu","orcid":null},"institutions":[{"id":"https://openalex.org/I90023481","display_name":"National Institute of Information and Communications Technology","ror":"https://ror.org/016bgq349","country_code":"JP","type":"facility","lineage":["https://openalex.org/I90023481"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Xinhui Hu","raw_affiliation_strings":["Spoken Language Communication Laboratory, National Institute of Information and Communications Technology, Kyoto, Japan","Spoken Language Communication Laboratory, National Institute of Information and Communications Technology (NICT), Kyoto, Japan"],"affiliations":[{"raw_affiliation_string":"Spoken Language Communication Laboratory, National Institute of Information and Communications Technology, Kyoto, Japan","institution_ids":["https://openalex.org/I90023481"]},{"raw_affiliation_string":"Spoken Language Communication Laboratory, National Institute of Information and Communications Technology (NICT), Kyoto, Japan","institution_ids":["https://openalex.org/I90023481"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011555779","display_name":"Youzheng Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I90023481","display_name":"National Institute of Information and Communications Technology","ror":"https://ror.org/016bgq349","country_code":"JP","type":"facility","lineage":["https://openalex.org/I90023481"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Youzheng Wu","raw_affiliation_strings":["Spoken Language Communication Laboratory, National Institute of Information and Communications Technology, Kyoto, Japan","Spoken Language Communication Laboratory, National Institute of Information and Communications Technology (NICT), Kyoto, Japan"],"affiliations":[{"raw_affiliation_string":"Spoken Language Communication Laboratory, National Institute of Information and Communications Technology, Kyoto, Japan","institution_ids":["https://openalex.org/I90023481"]},{"raw_affiliation_string":"Spoken Language Communication Laboratory, National Institute of Information and Communications Technology (NICT), Kyoto, Japan","institution_ids":["https://openalex.org/I90023481"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077037266","display_name":"Shigeki Matsuda","orcid":null},"institutions":[{"id":"https://openalex.org/I90023481","display_name":"National Institute of Information and Communications Technology","ror":"https://ror.org/016bgq349","country_code":"JP","type":"facility","lineage":["https://openalex.org/I90023481"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Shigeki Matsuda","raw_affiliation_strings":["Spoken Language Communication Laboratory, National Institute of Information and Communications Technology, Kyoto, Japan","Spoken Language Communication Laboratory, National Institute of Information and Communications Technology (NICT), Kyoto, Japan"],"affiliations":[{"raw_affiliation_string":"Spoken Language Communication Laboratory, National Institute of Information and Communications Technology, Kyoto, Japan","institution_ids":["https://openalex.org/I90023481"]},{"raw_affiliation_string":"Spoken Language Communication Laboratory, National Institute of Information and Communications Technology (NICT), Kyoto, Japan","institution_ids":["https://openalex.org/I90023481"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001601327","display_name":"Chiori Hori","orcid":"https://orcid.org/0000-0002-4201-7578"},"institutions":[{"id":"https://openalex.org/I90023481","display_name":"National Institute of Information and Communications Technology","ror":"https://ror.org/016bgq349","country_code":"JP","type":"facility","lineage":["https://openalex.org/I90023481"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Chiori Hori","raw_affiliation_strings":["Spoken Language Communication Laboratory, National Institute of Information and Communications Technology, Kyoto, Japan","Spoken Language Communication Laboratory, National Institute of Information and Communications Technology (NICT), Kyoto, Japan"],"affiliations":[{"raw_affiliation_string":"Spoken Language Communication Laboratory, National Institute of Information and Communications Technology, Kyoto, Japan","institution_ids":["https://openalex.org/I90023481"]},{"raw_affiliation_string":"Spoken Language Communication Laboratory, National Institute of Information and Communications Technology (NICT), Kyoto, Japan","institution_ids":["https://openalex.org/I90023481"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5108760549","display_name":"Hideki Kashioka","orcid":null},"institutions":[{"id":"https://openalex.org/I90023481","display_name":"National Institute of Information and Communications Technology","ror":"https://ror.org/016bgq349","country_code":"JP","type":"facility","lineage":["https://openalex.org/I90023481"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hideki Kashioka","raw_affiliation_strings":["Spoken Language Communication Laboratory, National Institute of Information and Communications Technology, Kyoto, Japan","Spoken Language Communication Laboratory, National Institute of Information and Communications Technology (NICT), Kyoto, Japan"],"affiliations":[{"raw_affiliation_string":"Spoken Language Communication Laboratory, National Institute of Information and Communications Technology, Kyoto, Japan","institution_ids":["https://openalex.org/I90023481"]},{"raw_affiliation_string":"Spoken Language Communication Laboratory, National Institute of Information and Communications Technology (NICT), Kyoto, Japan","institution_ids":["https://openalex.org/I90023481"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5041446566"],"corresponding_institution_ids":["https://openalex.org/I90023481"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.13143413,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"197","last_page":"200"},"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":0.9994999766349792,"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":0.9994000196456909,"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":0.9709933996200562},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8088281154632568},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.7402398586273193},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6428564786911011},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6140787601470947},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5839465856552124},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5285607576370239},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.47651660442352295},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.47084328532218933},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4552364647388458},{"id":"https://openalex.org/keywords/test-set","display_name":"Test set","score":0.44971713423728943},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.23130565881729126}],"concepts":[{"id":"https://openalex.org/C100279451","wikidata":"https://www.wikidata.org/wiki/Q372193","display_name":"Perplexity","level":3,"score":0.9709933996200562},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8088281154632568},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.7402398586273193},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6428564786911011},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6140787601470947},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5839465856552124},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5285607576370239},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.47651660442352295},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.47084328532218933},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4552364647388458},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.44971713423728943},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.23130565881729126},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iscslp.2012.6423548","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp.2012.6423548","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 8th International Symposium on Chinese Spoken Language Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.5699999928474426,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":7,"referenced_works":["https://openalex.org/W82600882","https://openalex.org/W149934508","https://openalex.org/W1611618274","https://openalex.org/W2117278770","https://openalex.org/W2153077320","https://openalex.org/W2394674404","https://openalex.org/W6677328538"],"related_works":["https://openalex.org/W2169518243","https://openalex.org/W2252095989","https://openalex.org/W4322096525","https://openalex.org/W2551914602","https://openalex.org/W4281893144","https://openalex.org/W2105076537","https://openalex.org/W2050138804","https://openalex.org/W2151348424","https://openalex.org/W1494910745","https://openalex.org/W1577263324"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3],"present":[4],"our":[5],"work":[6],"on":[7,66,107],"collecting":[8],"spontaneous":[9,82,111],"texts":[10,29,36,61],"from":[11,55],"the":[12,45,59,86,91,95,117,132,139,145],"Web":[13],"for":[14],"constructing":[15],"a":[16,20,40,79,99],"language":[17,87],"model":[18,88],"in":[19,43,157],"Chinese":[21],"speech":[22,102],"recognition":[23,103],"system.":[24],"The":[25],"selection":[26],"of":[27,81],"spontaneous-like":[28],"involves":[30],"two":[31],"steps:":[32],"First,":[33],"word-segmented":[34],"web":[35],"are":[37,48,62,74],"selected":[38,60,96],"using":[39],"perplexity-based":[41,147],"approach":[42,148],"which":[44],"style-related":[46],"words":[47,54,70],"strengthened":[49],"by":[50,76,94,129],"omitting":[51],"infrequent":[52],"topic":[53],"similarity":[56],"measurements.":[57],"Second,":[58],"then":[63],"clustered":[64],"based":[65],"non-noun":[67],"part-of-speech":[68],"(POS)":[69],"and":[71,98],"optimal":[72],"clusters":[73],"chosen":[75],"referring":[77],"to":[78,144],"set":[80],"seed":[83],"sentences.":[84],"Using":[85],"interpolated":[89],"with":[90,122,131,149],"one":[92],"trained":[93],"sentences":[97],"baseline":[100,133],"model,":[101],"evaluations":[104],"were":[105],"conducted":[106],"an":[108],"open":[109],"domain":[110],"test":[112],"set.":[113],"We":[114,135],"effectively":[115],"reduced":[116],"character":[118],"error":[119],"rate":[120],"(CER),":[121],"1.64%":[123],"absolute":[124,152],"(or":[125,153],"6.5%":[126],"relative)":[127,155],"reduction":[128,156],"comparison":[130],"model.":[134],"also":[136],"verified":[137],"that":[138],"proposed":[140],"method":[141],"is":[142],"superior":[143],"conventional":[146],"about":[150],"1%":[151],"4.0%":[154],"CER.":[158]},"counts_by_year":[{"year":2017,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}