{"id":"https://openalex.org/W2252265925","doi":"https://doi.org/10.18653/v1/d15-1091","title":"TSDPMM: Incorporating Prior Topic Knowledge into Dirichlet Process Mixture Models for Text Clustering","display_name":"TSDPMM: Incorporating Prior Topic Knowledge into Dirichlet Process Mixture Models for Text Clustering","publication_year":2015,"publication_date":"2015-01-01","ids":{"openalex":"https://openalex.org/W2252265925","doi":"https://doi.org/10.18653/v1/d15-1091","mag":"2252265925"},"language":"en","primary_location":{"id":"doi:10.18653/v1/d15-1091","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d15-1091","pdf_url":"https://www.aclweb.org/anthology/D15-1091.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/D15-1091.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5063307425","display_name":"Linmei Hu","orcid":"https://orcid.org/0000-0003-0993-8495"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Linmei Hu","raw_affiliation_strings":["STAR, Singapore","Dept. of Computer Sci. and Tech., Tsinghua University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"STAR, Singapore","institution_ids":[]},{"raw_affiliation_string":"Dept. of Computer Sci. and Tech., Tsinghua University, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003324011","display_name":"Juanzi Li","orcid":"https://orcid.org/0000-0002-6244-0664"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Juanzi Li","raw_affiliation_strings":["STAR, Singapore","Dept. of Computer Sci. and Tech., Tsinghua University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"STAR, Singapore","institution_ids":[]},{"raw_affiliation_string":"Dept. of Computer Sci. and Tech., Tsinghua University, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100418684","display_name":"Xiaoli Li","orcid":"https://orcid.org/0000-0002-0762-6562"},"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":"Xiaoli Li","raw_affiliation_strings":["Institute for Infocomm Research(I2R), A"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Infocomm Research(I2R), A","institution_ids":["https://openalex.org/I3005327000"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110485654","display_name":"Chao Shao","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chao Shao","raw_affiliation_strings":["STAR, Singapore","Dept. of Computer Sci. and Tech., Tsinghua University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"STAR, Singapore","institution_ids":[]},{"raw_affiliation_string":"Dept. of Computer Sci. and Tech., Tsinghua University, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5022836717","display_name":"Xuzhong Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xuzhong Wang","raw_affiliation_strings":["State Key Laboratory of Math. Eng. and Advanced Computing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Math. Eng. and Advanced Computing, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.823,"has_fulltext":true,"cited_by_count":6,"citation_normalized_percentile":{"value":0.74595428,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"787","last_page":"792"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11901","display_name":"Bayesian Methods and Mixture Models","score":0.9994999766349792,"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/T11901","display_name":"Bayesian Methods and Mixture Models","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/T11550","display_name":"Text and Document Classification Technologies","score":0.9836999773979187,"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":0.9818000197410583,"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/cluster-analysis","display_name":"Cluster analysis","score":0.8406819701194763},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7160142660140991},{"id":"https://openalex.org/keywords/topic-model","display_name":"Topic model","score":0.71200031042099},{"id":"https://openalex.org/keywords/latent-dirichlet-allocation","display_name":"Latent Dirichlet allocation","score":0.7046033143997192},{"id":"https://openalex.org/keywords/hierarchical-dirichlet-process","display_name":"Hierarchical Dirichlet process","score":0.6469970941543579},{"id":"https://openalex.org/keywords/dirichlet-process","display_name":"Dirichlet process","score":0.5882898569107056},{"id":"https://openalex.org/keywords/document-clustering","display_name":"Document clustering","score":0.584292471408844},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.579189121723175},{"id":"https://openalex.org/keywords/dirichlet-distribution","display_name":"Dirichlet distribution","score":0.5598275661468506},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.47102078795433044},{"id":"https://openalex.org/keywords/scheme","display_name":"Scheme (mathematics)","score":0.4580993950366974},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4273187816143036},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3492489755153656},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.34189099073410034},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1758282482624054}],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.8406819701194763},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7160142660140991},{"id":"https://openalex.org/C171686336","wikidata":"https://www.wikidata.org/wiki/Q3532085","display_name":"Topic model","level":2,"score":0.71200031042099},{"id":"https://openalex.org/C500882744","wikidata":"https://www.wikidata.org/wiki/Q269236","display_name":"Latent Dirichlet allocation","level":3,"score":0.7046033143997192},{"id":"https://openalex.org/C141318989","wikidata":"https://www.wikidata.org/wiki/Q5753066","display_name":"Hierarchical Dirichlet process","level":4,"score":0.6469970941543579},{"id":"https://openalex.org/C2781280628","wikidata":"https://www.wikidata.org/wiki/Q5280766","display_name":"Dirichlet process","level":3,"score":0.5882898569107056},{"id":"https://openalex.org/C177937566","wikidata":"https://www.wikidata.org/wiki/Q4223102","display_name":"Document clustering","level":3,"score":0.584292471408844},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.579189121723175},{"id":"https://openalex.org/C169214877","wikidata":"https://www.wikidata.org/wiki/Q981016","display_name":"Dirichlet distribution","level":3,"score":0.5598275661468506},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47102078795433044},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.4580993950366974},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4273187816143036},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3492489755153656},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.34189099073410034},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1758282482624054},{"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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"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":2,"locations":[{"id":"doi:10.18653/v1/d15-1091","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d15-1091","pdf_url":"https://www.aclweb.org/anthology/D15-1091.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.696.2428","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.696.2428","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://aclweb.org/anthology/D/D15/D15-1091.pdf","raw_type":"text"}],"best_oa_location":{"id":"doi:10.18653/v1/d15-1091","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d15-1091","pdf_url":"https://www.aclweb.org/anthology/D15-1091.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1828425977","display_name":null,"funder_award_id":"973 Program","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G263754083","display_name":null,"funder_award_id":"20131089256","funder_id":"https://openalex.org/F4320322392","funder_display_name":"Tsinghua University"},{"id":"https://openalex.org/G3310189042","display_name":null,"funder_award_id":"2014CB340504","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G4896575247","display_name":null,"funder_award_id":"2014CB340504","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320320883","display_name":"Agence Nationale de la Recherche","ror":"https://ror.org/00rbzpz17"},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320322392","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2252265925.pdf","grobid_xml":"https://content.openalex.org/works/W2252265925.grobid-xml"},"referenced_works_count":19,"referenced_works":["https://openalex.org/W49792935","https://openalex.org/W192837634","https://openalex.org/W258053484","https://openalex.org/W1506246224","https://openalex.org/W1880262756","https://openalex.org/W1967687583","https://openalex.org/W1969486090","https://openalex.org/W1989753615","https://openalex.org/W1995866178","https://openalex.org/W2057230177","https://openalex.org/W2061922307","https://openalex.org/W2080972498","https://openalex.org/W2089484716","https://openalex.org/W2110591510","https://openalex.org/W2126204609","https://openalex.org/W2158085718","https://openalex.org/W2540370807","https://openalex.org/W2963673689","https://openalex.org/W4231510805"],"related_works":["https://openalex.org/W4309228610","https://openalex.org/W2914864478","https://openalex.org/W2097627380","https://openalex.org/W2008338582","https://openalex.org/W4291700620","https://openalex.org/W1999586157","https://openalex.org/W22044811","https://openalex.org/W2625329765","https://openalex.org/W2255612897","https://openalex.org/W2766840109"],"abstract_inverted_index":{"Dirichlet":[0],"process":[1],"mixture":[2],"model":[3,74,100],"(DPM-M)":[4],"has":[5],"great":[6],"potential":[7,50],"for":[8,20],"detecting":[9],"the":[10,30,33,64],"underlying":[11],"structure":[12],"of":[13,25],"data.":[14],"Extensive":[15],"studies":[16],"have":[17,44],"applied":[18,104],"it":[19],"text":[21,68],"clustering":[22,88],"in":[23,54,105],"terms":[24],"topics.":[26],"However,":[27],"due":[28],"to":[29,59,66],"unsupervised":[31],"nature,":[32],"topic":[34],"clusters":[35],"are":[36],"always":[37],"less":[38],"satisfactory.":[39],"Considering":[40],"that":[41],"people":[42],"often":[43],"some":[45],"prior":[46],"knowledge":[47,62],"about":[48],"which":[49],"topics":[51],"should":[52],"exist":[53],"given":[55],"data,":[56],"we":[57],"aim":[58],"incorporate":[60],"such":[61],"into":[63],"DPMM":[65,99],"improve":[67],"clustering.":[69],"We":[70],"propose":[71],"a":[72,78,106],"novel":[73],"TSDPMM":[75,95],"based":[76],"on":[77,86],"new":[79],"seeded":[80],"Plya":[81],"urn":[82],"scheme.":[83],"Experimental":[84],"results":[85],"document":[87],"across":[89],"three":[90],"datasets":[91],"demonstrate":[92],"our":[93],"proposed":[94],"significantly":[96],"outperforms":[97],"stateof-the-art":[98],"and":[101],"can":[102],"be":[103],"lifelong":[107],"learning":[108],"framework.":[109]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1}],"updated_date":"2026-07-31T08:31:51.225901","created_date":"2025-10-10T00:00:00"}