{"id":"https://openalex.org/W2098876025","doi":"https://doi.org/10.1017/s1351324900002278","title":"Topic-based mixture language modelling","display_name":"Topic-based mixture language modelling","publication_year":1999,"publication_date":"1999-12-01","ids":{"openalex":"https://openalex.org/W2098876025","doi":"https://doi.org/10.1017/s1351324900002278","mag":"2098876025"},"language":"en","primary_location":{"id":"doi:10.1017/s1351324900002278","is_oa":true,"landing_page_url":"https://doi.org/10.1017/s1351324900002278","pdf_url":"https://www.cambridge.org/core/services/aop-cambridge-core/content/view/A26AD26F5DBE74575EB41483A9EABF5F/S1351324900002278a.pdf/div-class-title-topic-based-mixture-language-modelling-div.pdf","source":{"id":"https://openalex.org/S18088403","display_name":"Natural Language Engineering","issn_l":"1351-3249","issn":["1351-3249","1469-8110"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311721","host_organization_name":"Cambridge University Press","host_organization_lineage":["https://openalex.org/P4310311721","https://openalex.org/P4310311702"],"host_organization_lineage_names":["Cambridge University Press","University of Cambridge"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Natural Language Engineering","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://www.cambridge.org/core/services/aop-cambridge-core/content/view/A26AD26F5DBE74575EB41483A9EABF5F/S1351324900002278a.pdf/div-class-title-topic-based-mixture-language-modelling-div.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5047046960","display_name":"Yoshihiko Gotoh","orcid":"https://orcid.org/0000-0003-1668-0867"},"institutions":[{"id":"https://openalex.org/I91136226","display_name":"University of Sheffield","ror":"https://ror.org/05krs5044","country_code":"GB","type":"education","lineage":["https://openalex.org/I91136226"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"YOSHIHIKO GOTOH","raw_affiliation_strings":["Department of Computer Science, University of Sheffield, Regent Court, 211 Portobello Street, Sheffield S1 4DP, UK; e-mail:","Department of Computer Science, University of Sheffield, Regent Court, 211 Portobello Street, Sheffield, S1 4DP, UK"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Sheffield, Regent Court, 211 Portobello Street, Sheffield S1 4DP, UK; e-mail:","institution_ids":["https://openalex.org/I91136226"]},{"raw_affiliation_string":"Department of Computer Science, University of Sheffield, Regent Court, 211 Portobello Street, Sheffield, S1 4DP, UK","institution_ids":["https://openalex.org/I91136226"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5027442277","display_name":"Steve Renals","orcid":"https://orcid.org/0000-0002-8790-3389"},"institutions":[{"id":"https://openalex.org/I91136226","display_name":"University of Sheffield","ror":"https://ror.org/05krs5044","country_code":"GB","type":"education","lineage":["https://openalex.org/I91136226"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"STEVE RENALS","raw_affiliation_strings":["Department of Computer Science, University of Sheffield, Regent Court, 211 Portobello Street, Sheffield S1 4DP, UK; e-mail:","Department of Computer Science, University of Sheffield, Regent Court, 211 Portobello Street, Sheffield, S1 4DP, UK"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Sheffield, Regent Court, 211 Portobello Street, Sheffield S1 4DP, UK; e-mail:","institution_ids":["https://openalex.org/I91136226"]},{"raw_affiliation_string":"Department of Computer Science, University of Sheffield, Regent Court, 211 Portobello Street, Sheffield, S1 4DP, UK","institution_ids":["https://openalex.org/I91136226"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5047046960"],"corresponding_institution_ids":["https://openalex.org/I91136226"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":13,"citation_normalized_percentile":{"value":0.15649364,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"5","issue":"4","first_page":"355","last_page":"375"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","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"}},"topics":[{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","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"}},{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.998199999332428,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9922999739646912,"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":0.8932040929794312},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.719646692276001},{"id":"https://openalex.org/keywords/perplexity","display_name":"Perplexity","score":0.6929212808609009},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.6304974555969238},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6244599223136902},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5725666284561157},{"id":"https://openalex.org/keywords/latent-semantic-analysis","display_name":"Latent semantic analysis","score":0.5349764823913574},{"id":"https://openalex.org/keywords/probabilistic-latent-semantic-analysis","display_name":"Probabilistic latent semantic analysis","score":0.48606517910957336},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.4604763090610504},{"id":"https://openalex.org/keywords/topic-model","display_name":"Topic model","score":0.44890350103378296},{"id":"https://openalex.org/keywords/weighting","display_name":"Weighting","score":0.44044435024261475},{"id":"https://openalex.org/keywords/text-corpus","display_name":"Text corpus","score":0.4324853718280792},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.41733062267303467},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.34669554233551025}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8932040929794312},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.719646692276001},{"id":"https://openalex.org/C100279451","wikidata":"https://www.wikidata.org/wiki/Q372193","display_name":"Perplexity","level":3,"score":0.6929212808609009},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6304974555969238},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6244599223136902},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5725666284561157},{"id":"https://openalex.org/C170133592","wikidata":"https://www.wikidata.org/wiki/Q1806883","display_name":"Latent semantic analysis","level":2,"score":0.5349764823913574},{"id":"https://openalex.org/C112933361","wikidata":"https://www.wikidata.org/wiki/Q2845258","display_name":"Probabilistic latent semantic analysis","level":2,"score":0.48606517910957336},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.4604763090610504},{"id":"https://openalex.org/C171686336","wikidata":"https://www.wikidata.org/wiki/Q3532085","display_name":"Topic model","level":2,"score":0.44890350103378296},{"id":"https://openalex.org/C183115368","wikidata":"https://www.wikidata.org/wiki/Q856577","display_name":"Weighting","level":2,"score":0.44044435024261475},{"id":"https://openalex.org/C2474386","wikidata":"https://www.wikidata.org/wiki/Q461183","display_name":"Text corpus","level":2,"score":0.4324853718280792},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.41733062267303467},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.34669554233551025},{"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/C126838900","wikidata":"https://www.wikidata.org/wiki/Q77604","display_name":"Radiology","level":1,"score":0.0},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1017/s1351324900002278","is_oa":true,"landing_page_url":"https://doi.org/10.1017/s1351324900002278","pdf_url":"https://www.cambridge.org/core/services/aop-cambridge-core/content/view/A26AD26F5DBE74575EB41483A9EABF5F/S1351324900002278a.pdf/div-class-title-topic-based-mixture-language-modelling-div.pdf","source":{"id":"https://openalex.org/S18088403","display_name":"Natural Language Engineering","issn_l":"1351-3249","issn":["1351-3249","1469-8110"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311721","host_organization_name":"Cambridge University Press","host_organization_lineage":["https://openalex.org/P4310311721","https://openalex.org/P4310311702"],"host_organization_lineage_names":["Cambridge University Press","University of Cambridge"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Natural Language Engineering","raw_type":"journal-article"},{"id":"pmh:oai:eprints.whiterose.ac.uk:1578","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4306400854","display_name":"White Rose Research Online (University of Leeds, The University of Sheffield, University of York)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I2800616092","host_organization_name":"White Rose University Consortium","host_organization_lineage":["https://openalex.org/I2800616092"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"","raw_type":"Article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.36.5346","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.36.5346","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"ftp://ftp.dcs.shef.ac.uk/home/sjr/pubs/2000/jnle00.ps.gz","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.42.5119","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.42.5119","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.dcs.shef.ac.uk/~yg/./papers_ps1/jnle99.ps.gz","raw_type":"text"},{"id":"pmh:oai:era.ed.ac.uk:1842/1189","is_oa":false,"landing_page_url":"http://hdl.handle.net/1842/1189","pdf_url":null,"source":{"id":"https://openalex.org/S7407055182","display_name":"ERA","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"}],"best_oa_location":{"id":"doi:10.1017/s1351324900002278","is_oa":true,"landing_page_url":"https://doi.org/10.1017/s1351324900002278","pdf_url":"https://www.cambridge.org/core/services/aop-cambridge-core/content/view/A26AD26F5DBE74575EB41483A9EABF5F/S1351324900002278a.pdf/div-class-title-topic-based-mixture-language-modelling-div.pdf","source":{"id":"https://openalex.org/S18088403","display_name":"Natural Language Engineering","issn_l":"1351-3249","issn":["1351-3249","1469-8110"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311721","host_organization_name":"Cambridge University Press","host_organization_lineage":["https://openalex.org/P4310311721","https://openalex.org/P4310311702"],"host_organization_lineage_names":["Cambridge University Press","University of Cambridge"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Natural Language Engineering","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.8199999928474426,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2098876025.pdf","grobid_xml":"https://content.openalex.org/works/W2098876025.grobid-xml"},"referenced_works_count":39,"referenced_works":["https://openalex.org/W32217939","https://openalex.org/W166966826","https://openalex.org/W182840523","https://openalex.org/W1484670493","https://openalex.org/W1553387275","https://openalex.org/W1572100238","https://openalex.org/W1621933882","https://openalex.org/W1665921526","https://openalex.org/W1885411690","https://openalex.org/W1981367467","https://openalex.org/W1996903695","https://openalex.org/W1997841190","https://openalex.org/W2040058125","https://openalex.org/W2049633694","https://openalex.org/W2058616517","https://openalex.org/W2064580901","https://openalex.org/W2072773380","https://openalex.org/W2077312838","https://openalex.org/W2089468765","https://openalex.org/W2107743791","https://openalex.org/W2111842831","https://openalex.org/W2116236039","https://openalex.org/W2119907552","https://openalex.org/W2121227244","https://openalex.org/W2127314673","https://openalex.org/W2127836646","https://openalex.org/W2140842551","https://openalex.org/W2146610201","https://openalex.org/W2147152072","https://openalex.org/W2151315616","https://openalex.org/W2151348424","https://openalex.org/W2162965720","https://openalex.org/W2166698530","https://openalex.org/W2169004584","https://openalex.org/W2796837256","https://openalex.org/W2951328679","https://openalex.org/W4233135949","https://openalex.org/W4400191782","https://openalex.org/W6604774114"],"related_works":["https://openalex.org/W4293734197","https://openalex.org/W2588002110","https://openalex.org/W2169401934","https://openalex.org/W2111020819","https://openalex.org/W4206967254","https://openalex.org/W2921491680","https://openalex.org/W4214866631","https://openalex.org/W4285156758","https://openalex.org/W2171515436","https://openalex.org/W4205818640"],"abstract_inverted_index":{"This":[0],"paper":[1],"describes":[2],"an":[3,50,163],"approach":[4,27,84,153],"for":[5,23,85],"constructing":[6],"a":[7,54,177],"mixture":[8,55,86],"of":[9,17,39,56,66,117,132,158],"language":[10,58,87,123,160],"models":[11,21,59],"based":[12],"on":[13],"simple":[14],"statistical":[15,159],"notions":[16],"semantics":[18],"using":[19,145],"probabilistic":[20],"developed":[22],"information":[24,31,77,106],"retrieval.":[25],"The":[26,63],"encapsulates":[28],"corpus-derived":[29],"semantic":[30,139],"and":[32,53,80,95,122,129],"is":[33,60,69,91,107],"able":[34],"to":[35,70,81,100,172],"model":[36,168],"varying":[37],"styles":[38],"text.":[40],"Using":[41,162],"such":[42],"information,":[43],"the":[44,72,83,103,110,130,146,152,156,166],"corpus":[45],"texts":[46],"are":[47],"clustered":[48],"in":[49,98,109,180],"unsupervised":[51],"manner":[52],"topic-specific":[57],"automatically":[61],"created.":[62],"principal":[64],"contribution":[65],"this":[67],"work":[68],"characterise":[71],"document":[73],"space":[74],"resulting":[75],"from":[76],"retrieval":[78],"techniques":[79],"demonstrate":[82],"modelling.":[88,161],"A":[89],"comparison":[90],"made":[92],"between":[93],"manual":[94,120],"automatic":[96],"clustering":[97,121],"order":[99],"elucidate":[101],"how":[102],"global":[104],"content":[105],"expressed":[108],"space.":[111],"We":[112],"also":[113],"compare":[114],"(in":[115],"terms":[116],"association":[118],"with":[119,176],"modelling":[124],"accuracy)":[125],"alternative":[126],"term-weighting":[127],"schemes":[128],"effect":[131],"singular":[133],"value":[134],"decomposition":[135],"dimension":[136],"reduction":[137],"(latent":[138],"analysis).":[140],"Test":[141],"set":[142],"perplexity":[143],"results":[144],"British":[147],"National":[148],"Corpus":[149],"indicate":[150],"that":[151],"can":[154],"improve":[155],"potential":[157],"adaptive":[164],"procedure,":[165],"conventional":[167],"may":[169],"be":[170],"tuned":[171],"track":[173],"text":[174],"data":[175],"slight":[178],"increase":[179],"computational":[181],"cost.":[182]},"counts_by_year":[{"year":2013,"cited_by_count":1}],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-10-10T00:00:00"}