{"id":"https://openalex.org/W3007059124","doi":"https://doi.org/10.1109/tkde.2020.2976945","title":"Copula Guided Parallel Gibbs Sampling for Nonparametric and Coherent Topic Discovery","display_name":"Copula Guided Parallel Gibbs Sampling for Nonparametric and Coherent Topic Discovery","publication_year":2020,"publication_date":"2020-01-01","ids":{"openalex":"https://openalex.org/W3007059124","doi":"https://doi.org/10.1109/tkde.2020.2976945","mag":"3007059124"},"language":"en","primary_location":{"id":"doi:10.1109/tkde.2020.2976945","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tkde.2020.2976945","pdf_url":null,"source":{"id":"https://openalex.org/S30698027","display_name":"IEEE Transactions on Knowledge and Data Engineering","issn_l":"1041-4347","issn":["1041-4347","1558-2191","2326-3865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","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 Knowledge and Data Engineering","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/A5007173961","display_name":"Lihui Lin","orcid":"https://orcid.org/0000-0002-6285-3784"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lihui Lin","raw_affiliation_strings":["School of Data and Computer Science, Sun Yat-sen University, Guangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Data and Computer Science, Sun Yat-sen University, Guangzhou, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058291454","display_name":"Yanghui Rao","orcid":"https://orcid.org/0000-0003-1610-9599"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanghui Rao","raw_affiliation_strings":["School of Data and Computer Science, Sun Yat-sen University, Guangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Data and Computer Science, Sun Yat-sen University, Guangzhou, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013151488","display_name":"Haoran Xie","orcid":"https://orcid.org/0000-0003-0965-3617"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Haoran Xie","raw_affiliation_strings":["Department of Computing and Decision Sciences, Lingnan University, Tuen Mun, New Territories, Hong Kong SAR"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computing and Decision Sciences, Lingnan University, Tuen Mun, New Territories, Hong Kong SAR","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084348345","display_name":"Raymond Y.K. Lau","orcid":"https://orcid.org/0000-0002-5751-4550"},"institutions":[{"id":"https://openalex.org/I168719708","display_name":"City University of Hong Kong","ror":"https://ror.org/03q8dnn23","country_code":"HK","type":"education","lineage":["https://openalex.org/I168719708"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Raymond Yiu Keung Lau","raw_affiliation_strings":["Department of Information Systems, City University of Hong Kong, Tat Chee Avenue, Kowloon, Hong Kong SAR"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Information Systems, City University of Hong Kong, Tat Chee Avenue, Kowloon, Hong Kong SAR","institution_ids":["https://openalex.org/I168719708"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017205177","display_name":"Jian Yin","orcid":"https://orcid.org/0000-0002-1214-5384"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jian Yin","raw_affiliation_strings":["School of Data and Computer Science, Sun Yat-sen University, Guangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Data and Computer Science, Sun Yat-sen University, Guangzhou, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072482402","display_name":"Fu Lee Wang","orcid":"https://orcid.org/0000-0002-3976-0053"},"institutions":[{"id":"https://openalex.org/I8679417","display_name":"Hong Kong Metropolitan University","ror":"https://ror.org/0349bsm71","country_code":"HK","type":"education","lineage":["https://openalex.org/I8679417"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Fu Lee Wang","raw_affiliation_strings":["School of Science and Technology, Open University of Hong Kong, Ho Man Tin, Kowloon, Hong Kong SAR"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Science and Technology, Open University of Hong Kong, Ho Man Tin, Kowloon, Hong Kong SAR","institution_ids":["https://openalex.org/I8679417"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100404176","display_name":"Qing Li","orcid":"https://orcid.org/0000-0003-3370-471X"},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Qing Li","raw_affiliation_strings":["Department of Computing, Hong Kong Polytechnic University, Hung Hom, Kowloon, Hong Kong SAR"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computing, Hong Kong Polytechnic University, Hung Hom, Kowloon, Hong Kong SAR","institution_ids":["https://openalex.org/I14243506"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":2045,"currency":"USD","value_usd":2045},"apc_paid":null,"fwci":0.5687,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.7470775,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":93,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"1"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"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"}},"topics":[{"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9951000213623047,"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":0.9941999912261963,"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/copula","display_name":"Copula (linguistics)","score":0.7210460901260376},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.719581663608551},{"id":"https://openalex.org/keywords/gibbs-sampling","display_name":"Gibbs sampling","score":0.6918162107467651},{"id":"https://openalex.org/keywords/nonparametric-statistics","display_name":"Nonparametric statistics","score":0.5894648432731628},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4341810643672943},{"id":"https://openalex.org/keywords/econometrics","display_name":"Econometrics","score":0.3988840579986572},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.36289137601852417},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.35762932896614075},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.21845293045043945},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.14874836802482605}],"concepts":[{"id":"https://openalex.org/C17618745","wikidata":"https://www.wikidata.org/wiki/Q207509","display_name":"Copula (linguistics)","level":2,"score":0.7210460901260376},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.719581663608551},{"id":"https://openalex.org/C158424031","wikidata":"https://www.wikidata.org/wiki/Q1191905","display_name":"Gibbs sampling","level":3,"score":0.6918162107467651},{"id":"https://openalex.org/C102366305","wikidata":"https://www.wikidata.org/wiki/Q1097688","display_name":"Nonparametric statistics","level":2,"score":0.5894648432731628},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4341810643672943},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.3988840579986572},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.36289137601852417},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35762932896614075},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.21845293045043945},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.14874836802482605}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tkde.2020.2976945","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tkde.2020.2976945","pdf_url":null,"source":{"id":"https://openalex.org/S30698027","display_name":"IEEE Transactions on Knowledge and Data Engineering","issn_l":"1041-4347","issn":["1041-4347","1558-2191","2326-3865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","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 Knowledge and Data Engineering","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.6600000262260437,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":68,"referenced_works":["https://openalex.org/W1878153963","https://openalex.org/W2041590596","https://openalex.org/W2054333436","https://openalex.org/W2061603105","https://openalex.org/W2068123905","https://openalex.org/W2100163972","https://openalex.org/W2103587173","https://openalex.org/W2104210067","https://openalex.org/W2106706098","https://openalex.org/W2108456278","https://openalex.org/W2112050062","https://openalex.org/W2115087442","https://openalex.org/W2116628315","https://openalex.org/W2120636621","https://openalex.org/W2127492100","https://openalex.org/W2135537007","https://openalex.org/W2140660104","https://openalex.org/W2162057505","https://openalex.org/W2169606435","https://openalex.org/W2173681125","https://openalex.org/W2187741934","https://openalex.org/W2197590357","https://openalex.org/W2223881431","https://openalex.org/W2250533720","https://openalex.org/W2296146392","https://openalex.org/W2338185250","https://openalex.org/W2361559774","https://openalex.org/W2407111606","https://openalex.org/W2493916176","https://openalex.org/W2550969563","https://openalex.org/W2563583309","https://openalex.org/W2566384245","https://openalex.org/W2574301479","https://openalex.org/W2621133045","https://openalex.org/W2741172726","https://openalex.org/W2777166005","https://openalex.org/W2791947585","https://openalex.org/W2796254167","https://openalex.org/W2798311451","https://openalex.org/W2803437449","https://openalex.org/W2891585127","https://openalex.org/W2951312448","https://openalex.org/W2963223306","https://openalex.org/W2964119493","https://openalex.org/W4231510805","https://openalex.org/W6639402488","https://openalex.org/W6639619044","https://openalex.org/W6674922813","https://openalex.org/W6675301171","https://openalex.org/W6676175453","https://openalex.org/W6677144603","https://openalex.org/W6678007500","https://openalex.org/W6680954251","https://openalex.org/W6682357550","https://openalex.org/W6683528069","https://openalex.org/W6685356407","https://openalex.org/W6686958735","https://openalex.org/W6687459197","https://openalex.org/W6697246327","https://openalex.org/W6697359872","https://openalex.org/W6703548810","https://openalex.org/W6729474919","https://openalex.org/W6730972591","https://openalex.org/W6731303735","https://openalex.org/W6731883649","https://openalex.org/W6738975087","https://openalex.org/W6747136084","https://openalex.org/W6751854905"],"related_works":["https://openalex.org/W2804113700","https://openalex.org/W1556586489","https://openalex.org/W3107042086","https://openalex.org/W2153575119","https://openalex.org/W2036288595","https://openalex.org/W2096953155","https://openalex.org/W2775765116","https://openalex.org/W3122770326","https://openalex.org/W4300186142","https://openalex.org/W2888617444"],"abstract_inverted_index":{"Hierarchical":[0],"Dirichlet":[1,54],"Process":[2,97],"(HDP)":[3],"has":[4],"attracted":[5],"much":[6,61,194],"attention":[7],"in":[8,47,99,171],"the":[9,24,37,72,90,102,106,115,119,126,133,141,145,149,155,184,220,227,264,270,278],"research":[10],"community":[11],"of":[12,26,40,74,101,121,136,140,147,158,222,266,272],"natural":[13],"language":[14],"processing.":[15],"Given":[16],"a":[17,43,60,76,189,208,235,256],"corpus,":[18],"HDP":[19,58,87,93,216],"is":[20,81,144,160],"able":[21],"to":[22,83,113,187,206],"determine":[23],"number":[25,46,120,221],"topics":[27,122,223],"automatically,":[28],"possessing":[29],"an":[30],"important":[31],"feature":[32,135],"dubbed":[33],"nonparametric":[34,134],"that":[35,233,244],"overcomes":[36],"challenging":[38],"issue":[39],"manually":[41,123],"specifying":[42],"suitable":[44],"topic":[45,49,127,156,173,191,252],"parametric":[48],"models,":[50],"such":[51],"as":[52],"Latent":[53],"Allocation":[55],"(LDA).":[56],"Nevertheless,":[57],"requires":[59,112],"higher":[62],"computational":[63],"cost":[64],"than":[65],"LDA":[66],"for":[67,86,215],"parameter":[68],"estimation.":[69],"By":[70],"taking":[71],"advantage":[73],"multi-threading,":[75],"parallel":[77,108,211],"Gibbs":[78,109,212],"sampling":[79,110,213],"algorithm":[80,111,214],"proposed":[82],"estimate":[84],"parameters":[85],"based":[88],"on":[89,118,240,269],"equivalence":[91],"between":[92,152,231],"and":[94,196,225,250],"Gamma-Gamma":[95],"Poisson":[96],"(G2PP)":[98],"terms":[100],"generative":[103],"process.":[104],"Unfortunately,":[105],"above":[107,142],"apply":[114],"finite":[116],"approximation":[117],"(i.e.,":[124],"predefine":[125],"number),":[128],"thus":[129],"can":[130,218],"not":[131],"retain":[132],"HDP.":[137],"Another":[138],"drawback":[139],"models":[143],"lack":[146],"capturing":[148],"semantic":[150,229,274],"dependencies":[151,230,275],"words,":[153],"because":[154],"assignment":[157],"words":[159,232],"independent":[161],"with":[162,255,282],"each":[163],"other.":[164],"Although":[165],"some":[166],"works":[167],"have":[168],"been":[169],"done":[170],"phrase-based":[172,287],"modelling,":[174],"these":[175],"existing":[176],"methods":[177],"are":[178],"still":[179],"limited":[180],"by":[181,276,285],"either":[182],"enforcing":[183],"entire":[185],"phrase":[186,198],"share":[188],"common":[190],"or":[192],"requiring":[193],"complex":[195],"time-consuming":[197],"mining":[199],"methods.":[200],"In":[201,260],"this":[202],"paper,":[203],"we":[204,262],"aim":[205],"develop":[207],"copula":[209],"guided":[210],"which":[217],"adjust":[219],"dynamically":[224],"capture":[226],"latent":[228],"compose":[234],"coherent":[236],"segment.":[237],"Extensive":[238],"experiments":[239],"real-world":[241],"datasets":[242],"indicate":[243],"our":[245,267],"method":[246,268],"achieves":[247],"low":[248],"perplexities":[249],"high":[251],"coherence":[253],"scores":[254],"small":[257],"time":[258],"cost.":[259],"addition,":[261],"validate":[263],"effectiveness":[265],"modelling":[271],"word":[273],"comparing":[277],"extracted":[279],"topical":[280],"phrases":[281],"those":[283],"learned":[284],"state-of-the-art":[286],"baselines.":[288]},"counts_by_year":[{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":2}],"updated_date":"2026-08-28T12:50:07.497085","created_date":"2025-10-10T00:00:00"}