{"id":"https://openalex.org/W4220966911","doi":"https://doi.org/10.1145/3502727","title":"Stochastic Variational Optimization of a Hierarchical Dirichlet Process Latent Beta-Liouville Topic Model","display_name":"Stochastic Variational Optimization of a Hierarchical Dirichlet Process Latent Beta-Liouville Topic Model","publication_year":2022,"publication_date":"2022-03-09","ids":{"openalex":"https://openalex.org/W4220966911","doi":"https://doi.org/10.1145/3502727"},"language":"en","primary_location":{"id":"doi:10.1145/3502727","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3502727","pdf_url":null,"source":{"id":"https://openalex.org/S41523882","display_name":"ACM Transactions on Knowledge Discovery from Data","issn_l":"1556-4681","issn":["1556-4681","1556-472X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Knowledge Discovery from Data","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/A5065896848","display_name":"Koffi Eddy Ihou","orcid":"https://orcid.org/0000-0002-4678-4248"},"institutions":[{"id":"https://openalex.org/I60158472","display_name":"Concordia University","ror":"https://ror.org/0420zvk78","country_code":"CA","type":"education","lineage":["https://openalex.org/I60158472"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Koffi Eddy Ihou","raw_affiliation_strings":["Concordia University, Montreal, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Concordia University, Montreal, Canada","institution_ids":["https://openalex.org/I60158472"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008962576","display_name":"Manar Amayri","orcid":"https://orcid.org/0000-0002-5610-8833"},"institutions":[{"id":"https://openalex.org/I106785703","display_name":"Institut polytechnique de Grenoble","ror":"https://ror.org/05sbt2524","country_code":"FR","type":"education","lineage":["https://openalex.org/I106785703","https://openalex.org/I899635006"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Manar Amayri","raw_affiliation_strings":["Grenoble Institute of Technology, Grenoble, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Grenoble Institute of Technology, Grenoble, France","institution_ids":["https://openalex.org/I106785703"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5090600716","display_name":"Nizar Bouguila","orcid":"https://orcid.org/0000-0001-7224-7940"},"institutions":[{"id":"https://openalex.org/I60158472","display_name":"Concordia University","ror":"https://ror.org/0420zvk78","country_code":"CA","type":"education","lineage":["https://openalex.org/I60158472"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Nizar Bouguila","raw_affiliation_strings":["Concordia University, Montreal, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Concordia University, Montreal, Canada","institution_ids":["https://openalex.org/I60158472"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.5249,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.69286537,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"16","issue":"5","first_page":"1","last_page":"48"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11901","display_name":"Bayesian Methods and Mixture Models","score":0.9995999932289124,"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/T11901","display_name":"Bayesian Methods and Mixture Models","score":0.9995999932289124,"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":0.9905999898910522,"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":0.9850999712944031,"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":0.7915116548538208},{"id":"https://openalex.org/keywords/dirichlet-process","display_name":"Dirichlet process","score":0.7186354398727417},{"id":"https://openalex.org/keywords/hierarchical-dirichlet-process","display_name":"Hierarchical Dirichlet process","score":0.6984756588935852},{"id":"https://openalex.org/keywords/topic-model","display_name":"Topic model","score":0.6426383852958679},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5604650378227234},{"id":"https://openalex.org/keywords/measure","display_name":"Measure (data warehouse)","score":0.5515267848968506},{"id":"https://openalex.org/keywords/dirichlet-distribution","display_name":"Dirichlet distribution","score":0.5434532165527344},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.4913703501224518},{"id":"https://openalex.org/keywords/prior-probability","display_name":"Prior probability","score":0.47709327936172485},{"id":"https://openalex.org/keywords/parametric-statistics","display_name":"Parametric statistics","score":0.4625093340873718},{"id":"https://openalex.org/keywords/bayesian-inference","display_name":"Bayesian inference","score":0.4285467863082886},{"id":"https://openalex.org/keywords/posterior-probability","display_name":"Posterior probability","score":0.4279443621635437},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.38911664485931396},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.3706849217414856},{"id":"https://openalex.org/keywords/applied-mathematics","display_name":"Applied mathematics","score":0.32886508107185364},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2966247797012329},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.20915842056274414},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.13153532147407532}],"concepts":[{"id":"https://openalex.org/C500882744","wikidata":"https://www.wikidata.org/wiki/Q269236","display_name":"Latent Dirichlet allocation","level":3,"score":0.7915116548538208},{"id":"https://openalex.org/C2781280628","wikidata":"https://www.wikidata.org/wiki/Q5280766","display_name":"Dirichlet process","level":3,"score":0.7186354398727417},{"id":"https://openalex.org/C141318989","wikidata":"https://www.wikidata.org/wiki/Q5753066","display_name":"Hierarchical Dirichlet process","level":4,"score":0.6984756588935852},{"id":"https://openalex.org/C171686336","wikidata":"https://www.wikidata.org/wiki/Q3532085","display_name":"Topic model","level":2,"score":0.6426383852958679},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5604650378227234},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.5515267848968506},{"id":"https://openalex.org/C169214877","wikidata":"https://www.wikidata.org/wiki/Q981016","display_name":"Dirichlet distribution","level":3,"score":0.5434532165527344},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.4913703501224518},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.47709327936172485},{"id":"https://openalex.org/C117251300","wikidata":"https://www.wikidata.org/wiki/Q1849855","display_name":"Parametric statistics","level":2,"score":0.4625093340873718},{"id":"https://openalex.org/C160234255","wikidata":"https://www.wikidata.org/wiki/Q812535","display_name":"Bayesian inference","level":3,"score":0.4285467863082886},{"id":"https://openalex.org/C57830394","wikidata":"https://www.wikidata.org/wiki/Q278079","display_name":"Posterior probability","level":3,"score":0.4279443621635437},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.38911664485931396},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.3706849217414856},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.32886508107185364},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2966247797012329},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.20915842056274414},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.13153532147407532},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C182310444","wikidata":"https://www.wikidata.org/wiki/Q1332643","display_name":"Boundary value problem","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3502727","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3502727","pdf_url":null,"source":{"id":"https://openalex.org/S41523882","display_name":"ACM Transactions on Knowledge Discovery from Data","issn_l":"1556-4681","issn":["1556-4681","1556-472X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Knowledge Discovery from Data","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.46000000834465027}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":51,"referenced_works":["https://openalex.org/W166614460","https://openalex.org/W178169250","https://openalex.org/W203054622","https://openalex.org/W1601795611","https://openalex.org/W1783453637","https://openalex.org/W1828567212","https://openalex.org/W1880262756","https://openalex.org/W1972525513","https://openalex.org/W1972622791","https://openalex.org/W1989387811","https://openalex.org/W2000930721","https://openalex.org/W2001272401","https://openalex.org/W2001975024","https://openalex.org/W2005902041","https://openalex.org/W2025653016","https://openalex.org/W2029400613","https://openalex.org/W2030922352","https://openalex.org/W2054333436","https://openalex.org/W2055337076","https://openalex.org/W2065743703","https://openalex.org/W2069429561","https://openalex.org/W2078719085","https://openalex.org/W2087309226","https://openalex.org/W2130428211","https://openalex.org/W2143869282","https://openalex.org/W2144100511","https://openalex.org/W2144245426","https://openalex.org/W2150286230","https://openalex.org/W2151245724","https://openalex.org/W2151967501","https://openalex.org/W2153164668","https://openalex.org/W2154099718","https://openalex.org/W2158266063","https://openalex.org/W2163021329","https://openalex.org/W2166851633","https://openalex.org/W2174706414","https://openalex.org/W2255966421","https://openalex.org/W2517224595","https://openalex.org/W2544994990","https://openalex.org/W2604738573","https://openalex.org/W2618735189","https://openalex.org/W2779791408","https://openalex.org/W2789871865","https://openalex.org/W2895966686","https://openalex.org/W2907966865","https://openalex.org/W2909858298","https://openalex.org/W2912762941","https://openalex.org/W2975042594","https://openalex.org/W2990140544","https://openalex.org/W3045464143","https://openalex.org/W6682569104"],"related_works":["https://openalex.org/W2813472416","https://openalex.org/W2914864478","https://openalex.org/W2097627380","https://openalex.org/W1999586157","https://openalex.org/W4291700620","https://openalex.org/W22044811","https://openalex.org/W2625329765","https://openalex.org/W2529577912","https://openalex.org/W2766840109","https://openalex.org/W2955328590"],"abstract_inverted_index":{"In":[0,26,55,217],"topic":[1,19,32,77,88,99,249,316,319,361],"models,":[2],"collections":[3,254],"are":[4,44,164],"organized":[5],"as":[6,11,36,81,113,193,314,390],"documents":[7,73,98,257,387],"where":[8,90],"they":[9,392],"arise":[10],"mixtures":[12,100],"over":[13,23,125],"latent":[14],"clusters":[15],"called":[16],"topics.":[17],"A":[18],"is":[20,210,279,356,375],"a":[21,84,114,126,309,376,399],"distribution":[22],"the":[24,60,91,119,132,137,144,165,172,175,179,186,190,196,206,265,274,283,293,297,300,303,315,323,328,334,343,357,366,372,379],"vocabulary.":[25],"large-scale":[27],"applications,":[28],"parametric":[29,76,360],"or":[30],"finite":[31],"mixture":[33],"models":[34,97],"such":[35,313],"LDA":[37],"(latent":[38],"Dirichlet":[39,94,215],"allocation)":[40],"and":[41,66,153,167,318,325,402],"its":[42,228,277],"variants":[43],"very":[45],"restrictive":[46],"in":[47,74,136,150,264,365,398],"performance":[48,275,335,355],"due":[49],"to":[50,63,170,185,195,219,246,273,321,382],"their":[51,102],"reduced":[52],"hypothesis":[53],"space.":[54,128],"this":[56],"article,":[57],"we":[58,156,200,306],"address":[59],"problem":[61],"related":[62],"model":[64,89,232,298,338],"selection":[65],"sharing":[67],"ability":[68,381],"of":[69,139,205,227,255,276,285,296,302,311,327,336,371,378],"topics":[70,141,329],"across":[71],"multiple":[72],"standard":[75,207,344],"models.":[78,362],"We":[79,331,347],"propose":[80,109],"an":[82,202,234],"alternative":[83],"BNP":[85],"(Bayesian":[86],"nonparametric)":[87],"HDP":[92,173,208],"(hierarchical":[93],"process)":[95,124],"prior":[96,192],"through":[101],"multinomials":[103],"on":[104,213,239],"infinite":[105],"simplex.":[106],"We,":[107],"therefore,":[108],"asymmetric":[110,288],"BL":[111,191,353],"(Beta-Liouville)":[112],"diffuse":[115,187],"base":[116],"measure":[117,188],"at":[118,241],"corpus":[120,145],"level":[121],"DP":[122],"(Dirichlet":[123],"measurable":[127],"This":[129],"step":[130],"illustrates":[131],"highly":[133],"heterogeneous":[134],"structure":[135],"set":[138],"all":[140],"that":[142,209,349],"describes":[143],"probability":[146,160,301],"measure.":[147],"For":[148],"consistency":[149],"posterior":[151],"inference":[152,245],"predictive":[154,266,294,369],"distributions,":[155],"efficiently":[157,383],"characterize":[158,384],"random":[159,182],"measures":[161],"whose":[162],"limits":[163],"global":[166],"local":[168],"DPs":[169],"approximate":[171],"from":[174],"stick-breaking":[176],"formulation":[177],"with":[178,189,258,282],"GEM":[180],"(Griffiths-Engen-McCloskey)":[181],"variables.":[183],"Due":[184],"conjugate":[194],"count":[197],"data":[198],"distribution,":[199],"obtain":[201],"improved":[203],"version":[204],"usually":[211],"based":[212,238],"symmetric":[214,345],"(Dir).":[216],"addition,":[218],"improve":[220,322],"coordinate":[221],"ascent":[222],"framework":[223],"while":[224],"taking":[225],"advantage":[226],"deterministic":[229],"nature,":[230],"our":[231,286,337],"implements":[233],"online":[235,350],"optimization":[236],"method":[237],"stochastic,":[240],"document":[242,269],"level,":[243],"variational":[244],"accommodate":[247],"fast":[248],"learning":[250],"when":[251,271],"processing":[252],"large":[253],"text":[256],"natural":[259],"gradient.":[260],"The":[261,363],"high":[262],"value":[263],"likelihood":[267],"per":[268],"obtained":[270],"compared":[272,333],"competitors":[278],"also":[280,307,332],"consistent":[281],"robustness":[284],"fully":[287],"BL-based":[289],"HDP.":[290],"While":[291],"insuring":[292],"accuracy":[295,364],"using":[299,339],"held-out":[304],"documents,":[305],"added":[308],"combination":[310],"metrics":[312,341],"coherence":[317],"diversity":[320],"quality":[324],"interpretability":[326],"discovered.":[330],"these":[340],"against":[342],"LDA.":[346],"show":[348],"HDP-LBLA":[351],"(Latent":[352],"Allocation)\u2019s":[354],"asymptote":[358],"for":[359,406],"results":[367],"(improved":[368],"distributions":[370],"held":[373],"out)":[374],"product":[377],"model\u2019s":[380],"dependency":[385],"between":[386],"(topic":[388],"correlation)":[389],"now":[391],"can":[393],"easily":[394],"share":[395],"topics,":[396],"resulting":[397],"much":[400],"robust":[401],"realistic":[403],"compression":[404],"algorithm":[405],"information":[407],"modeling.":[408]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2023,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}