{"id":"https://openalex.org/W2154607549","doi":"https://doi.org/10.1109/iscslp.2010.5684904","title":"Building topic mixture language models using the document soft classification notion of topic models","display_name":"Building topic mixture language models using the document soft classification notion of topic models","publication_year":2010,"publication_date":"2010-11-01","ids":{"openalex":"https://openalex.org/W2154607549","doi":"https://doi.org/10.1109/iscslp.2010.5684904","mag":"2154607549"},"language":"en","primary_location":{"id":"doi:10.1109/iscslp.2010.5684904","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp.2010.5684904","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 7th 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/A5038172417","display_name":"Shuanhu Bai","orcid":null},"institutions":[{"id":"https://openalex.org/I3005327000","display_name":"Institute for Infocomm Research","ror":"https://ror.org/053rfa017","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3005327000","https://openalex.org/I91275662"]}],"countries":["SG"],"is_corresponding":true,"raw_author_name":"Shuanhu Bai","raw_affiliation_strings":["Institute for Infocomm Research, Singapore"],"affiliations":[{"raw_affiliation_string":"Institute for Infocomm Research, Singapore","institution_ids":["https://openalex.org/I3005327000"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113828649","display_name":"Cheung-Chi Leung","orcid":null},"institutions":[{"id":"https://openalex.org/I3005327000","display_name":"Institute for Infocomm Research","ror":"https://ror.org/053rfa017","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3005327000","https://openalex.org/I91275662"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Cheung-Chi Leung","raw_affiliation_strings":["Institute for Infocomm Research, Singapore"],"affiliations":[{"raw_affiliation_string":"Institute for Infocomm Research, Singapore","institution_ids":["https://openalex.org/I3005327000"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103086620","display_name":"Chien-Lin Huang","orcid":"https://orcid.org/0000-0003-3157-4173"},"institutions":[{"id":"https://openalex.org/I3005327000","display_name":"Institute for Infocomm Research","ror":"https://ror.org/053rfa017","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3005327000","https://openalex.org/I91275662"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Chien-Lin Huang","raw_affiliation_strings":["Institute for Infocomm Research, Singapore"],"affiliations":[{"raw_affiliation_string":"Institute for Infocomm Research, Singapore","institution_ids":["https://openalex.org/I3005327000"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100749735","display_name":"Bin Ma","orcid":"https://orcid.org/0000-0002-9223-9654"},"institutions":[{"id":"https://openalex.org/I3005327000","display_name":"Institute for Infocomm Research","ror":"https://ror.org/053rfa017","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3005327000","https://openalex.org/I91275662"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Bin Ma","raw_affiliation_strings":["Institute for Infocomm Research, Singapore"],"affiliations":[{"raw_affiliation_string":"Institute for Infocomm Research, Singapore","institution_ids":["https://openalex.org/I3005327000"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032690182","display_name":"Haizhou Li","orcid":"https://orcid.org/0000-0001-9158-9401"},"institutions":[{"id":"https://openalex.org/I3005327000","display_name":"Institute for Infocomm Research","ror":"https://ror.org/053rfa017","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3005327000","https://openalex.org/I91275662"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Haizhou Li","raw_affiliation_strings":["Institute for Infocomm Research, Singapore"],"affiliations":[{"raw_affiliation_string":"Institute for Infocomm Research, Singapore","institution_ids":["https://openalex.org/I3005327000"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5038172417"],"corresponding_institution_ids":["https://openalex.org/I3005327000"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.14784372,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"3","issue":null,"first_page":"229","last_page":"232"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","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"}},"topics":[{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","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/T10181","display_name":"Natural Language Processing Techniques","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/T10201","display_name":"Speech Recognition and Synthesis","score":0.994700014591217,"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/latent-dirichlet-allocation","display_name":"Latent Dirichlet allocation","score":0.8723787069320679},{"id":"https://openalex.org/keywords/topic-model","display_name":"Topic model","score":0.8533369898796082},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8201756477355957},{"id":"https://openalex.org/keywords/probabilistic-latent-semantic-analysis","display_name":"Probabilistic latent semantic analysis","score":0.7205340266227722},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6883381009101868},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5951709151268005},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5915709137916565},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5806882977485657},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5206443667411804},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.481821209192276},{"id":"https://openalex.org/keywords/n-gram","display_name":"n-gram","score":0.4647004008293152},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.4256686568260193},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3415992259979248}],"concepts":[{"id":"https://openalex.org/C500882744","wikidata":"https://www.wikidata.org/wiki/Q269236","display_name":"Latent Dirichlet allocation","level":3,"score":0.8723787069320679},{"id":"https://openalex.org/C171686336","wikidata":"https://www.wikidata.org/wiki/Q3532085","display_name":"Topic model","level":2,"score":0.8533369898796082},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8201756477355957},{"id":"https://openalex.org/C112933361","wikidata":"https://www.wikidata.org/wiki/Q2845258","display_name":"Probabilistic latent semantic analysis","level":2,"score":0.7205340266227722},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6883381009101868},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5951709151268005},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5915709137916565},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5806882977485657},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5206443667411804},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.481821209192276},{"id":"https://openalex.org/C117884012","wikidata":"https://www.wikidata.org/wiki/Q94489","display_name":"n-gram","level":3,"score":0.4647004008293152},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.4256686568260193},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3415992259979248},{"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/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iscslp.2010.5684904","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp.2010.5684904","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 7th International Symposium on Chinese Spoken Language Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7699999809265137,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W85801758","https://openalex.org/W1644652583","https://openalex.org/W1880262756","https://openalex.org/W2099061358","https://openalex.org/W2104210067","https://openalex.org/W2107743791","https://openalex.org/W2130696866","https://openalex.org/W2147766635","https://openalex.org/W2159382562","https://openalex.org/W2168277387","https://openalex.org/W3145733519","https://openalex.org/W4233135949","https://openalex.org/W6603500903","https://openalex.org/W6636890138","https://openalex.org/W6639619044","https://openalex.org/W6674990170","https://openalex.org/W6679505441"],"related_works":["https://openalex.org/W1551384396","https://openalex.org/W2921491680","https://openalex.org/W2251863249","https://openalex.org/W4291700620","https://openalex.org/W2132052677","https://openalex.org/W3159709618","https://openalex.org/W2888805565","https://openalex.org/W4396666968","https://openalex.org/W2110027950","https://openalex.org/W2043781532"],"abstract_inverted_index":{"We":[0],"present":[1],"a":[2,19,31],"topic":[3,16,32,82,92],"mixture":[4],"language":[5,66],"modeling":[6,33,76],"approach":[7,94],"making":[8],"use":[9,90],"of":[10,15],"the":[11,48,58,70,85,97,104,108],"soft":[12,27],"classification":[13,28],"notion":[14],"models.":[17,99],"Given":[18],"text":[20],"document":[21,26],"set,":[22],"we":[23,51,62,80,89],"first":[24],"perform":[25,81],"by":[29],"applying":[30],"process":[34],"such":[35],"as":[36],"probabilistic":[37],"latent":[38,43],"semantic":[39],"analyses":[40],"(PLSA)":[41],"or":[42],"Dirichlet":[44],"allocation":[45],"(LDA)":[46],"on":[47],"dataset.":[49],"Then":[50],"can":[52],"derive":[53],"topic-specific":[54,64,98],"n-gram":[55,65,71,75],"counts":[56,72],"from":[57,69,84],"classified":[59],"texts.":[60],"Finally":[61],"build":[63],"models":[67],"(LM)":[68],"using":[73],"traditional":[74],"approach.":[77],"In":[78],"decoding":[79],"inference":[83],"processing":[86],"context,":[87],"and":[88],"unsupervised":[91,111],"adaptation":[93,112],"to":[95],"combine":[96],"Experimental":[100],"results":[101],"show":[102],"that":[103],"suggested":[105],"method":[106],"outperforms":[107],"state-of-the-art":[109],"topic-model-based":[110],"approaches.":[113]},"counts_by_year":[{"year":2014,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}