{"id":"https://openalex.org/W3042602466","doi":"https://doi.org/10.1145/3394486.3403242","title":"Hierarchical Topic Mining via Joint Spherical Tree and Text Embedding","display_name":"Hierarchical Topic Mining via Joint Spherical Tree and Text Embedding","publication_year":2020,"publication_date":"2020-08-20","ids":{"openalex":"https://openalex.org/W3042602466","doi":"https://doi.org/10.1145/3394486.3403242","mag":"3042602466"},"language":"en","primary_location":{"id":"doi:10.1145/3394486.3403242","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3394486.3403242","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3394486.3403242","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3394486.3403242","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Yu Meng","orcid":null},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Yu Meng","raw_affiliation_strings":["University of Illinois at Urbana-Champaign, Champaign, IL, USA"],"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign, Champaign, IL, USA","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yunyi Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yunyi Zhang","raw_affiliation_strings":["University of Illinois at Urbana-Champaign, Champaign, IL, USA"],"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign, Champaign, IL, USA","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jiaxin Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jiaxin Huang","raw_affiliation_strings":["University of Illinois at Urbana-Champaign, Champaign, IL, USA"],"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign, Champaign, IL, USA","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yu Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yu Zhang","raw_affiliation_strings":["University of Illinois at Urbana-Champaign, Champaign, IL, USA"],"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign, Champaign, IL, USA","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Chao Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chao Zhang","raw_affiliation_strings":["Georgia Institute of Technology, Atlanta, GA, USA"],"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology, Atlanta, GA, USA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"last","author":{"id":null,"display_name":"Jiawei Han","orcid":null},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jiawei Han","raw_affiliation_strings":["University of Illinois at Urbana-Champaign, Champaign, IL, USA"],"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign, Champaign, IL, USA","institution_ids":["https://openalex.org/I157725225"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I157725225"],"apc_list":null,"apc_paid":null,"fwci":4.2141,"has_fulltext":true,"cited_by_count":56,"citation_normalized_percentile":{"value":0.95148564,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"1908","last_page":"1917"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9991000294685364,"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":0.9991000294685364,"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":0.9990000128746033,"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":0.993399977684021,"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/topic-model","display_name":"Topic model","score":0.7860000133514404},{"id":"https://openalex.org/keywords/hierarchy","display_name":"Hierarchy","score":0.7527999877929688},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.6294999718666077},{"id":"https://openalex.org/keywords/tree","display_name":"Tree (set theory)","score":0.614300012588501},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.6040999889373779},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.546500027179718},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.5184000134468079},{"id":"https://openalex.org/keywords/tree-structure","display_name":"Tree structure","score":0.4659000039100647}],"concepts":[{"id":"https://openalex.org/C171686336","wikidata":"https://www.wikidata.org/wiki/Q3532085","display_name":"Topic model","level":2,"score":0.7860000133514404},{"id":"https://openalex.org/C31170391","wikidata":"https://www.wikidata.org/wiki/Q188619","display_name":"Hierarchy","level":2,"score":0.7527999877929688},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7383000254631042},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6294999718666077},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.614300012588501},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.6040999889373779},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.546500027179718},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.5184000134468079},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5098000168800354},{"id":"https://openalex.org/C163797641","wikidata":"https://www.wikidata.org/wiki/Q2067937","display_name":"Tree structure","level":3,"score":0.4659000039100647},{"id":"https://openalex.org/C144986985","wikidata":"https://www.wikidata.org/wiki/Q871236","display_name":"Hierarchical database model","level":2,"score":0.4487999975681305},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4138000011444092},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.4077000021934509},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.3781999945640564},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.37119999527931213},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3709999918937683},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.34630000591278076},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3386000096797943},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.3260999917984009},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.3230000138282776},{"id":"https://openalex.org/C124527596","wikidata":"https://www.wikidata.org/wiki/Q17029359","display_name":"Hierarchical control system","level":3,"score":0.305400013923645},{"id":"https://openalex.org/C500882744","wikidata":"https://www.wikidata.org/wiki/Q269236","display_name":"Latent Dirichlet allocation","level":3,"score":0.2994000017642975},{"id":"https://openalex.org/C92835128","wikidata":"https://www.wikidata.org/wiki/Q1277447","display_name":"Hierarchical clustering","level":3,"score":0.2822999954223633},{"id":"https://openalex.org/C2474386","wikidata":"https://www.wikidata.org/wiki/Q461183","display_name":"Text corpus","level":2,"score":0.28060001134872437},{"id":"https://openalex.org/C2780217385","wikidata":"https://www.wikidata.org/wiki/Q2389284","display_name":"Hierarchical organization","level":2,"score":0.26930001378059387}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3394486.3403242","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3394486.3403242","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3394486.3403242","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2007.09536","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2007.09536","pdf_url":"https://arxiv.org/pdf/2007.09536","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"}],"best_oa_location":{"id":"doi:10.1145/3394486.3403242","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3394486.3403242","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3394486.3403242","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1472423617","display_name":null,"funder_award_id":"FA8750-19-2-1004","funder_id":"https://openalex.org/F4320332180","funder_display_name":"Defense Advanced Research Projects Agency"},{"id":"https://openalex.org/G2631557179","display_name":null,"funder_award_id":"IIS 16-18481,IIS 17-04532,IIS 17-41317","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G427511869","display_name":null,"funder_award_id":"IIS 17-04532","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G4713059963","display_name":null,"funder_award_id":"FA8750","funder_id":"https://openalex.org/F4320332180","funder_display_name":"Defense Advanced Research Projects Agency"},{"id":"https://openalex.org/G5490100290","display_name":null,"funder_award_id":"HDTRA11810026","funder_id":"https://openalex.org/F4320332186","funder_display_name":"Defense Threat Reduction Agency"},{"id":"https://openalex.org/G6415453432","display_name":null,"funder_award_id":"IIS 17-41317","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G6541015203","display_name":null,"funder_award_id":"HDTRA1","funder_id":"https://openalex.org/F4320332186","funder_display_name":"Defense Threat Reduction Agency"},{"id":"https://openalex.org/G7391348854","display_name":null,"funder_award_id":"FA8750-19-2-1004,W911NF-17-C-0099","funder_id":"https://openalex.org/F4320332180","funder_display_name":"Defense Advanced Research Projects Agency"},{"id":"https://openalex.org/G7903051118","display_name":null,"funder_award_id":"IIS 16-18481","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8175839138","display_name":null,"funder_award_id":"No. W911NF-17-C-0099","funder_id":"https://openalex.org/F4320332180","funder_display_name":"Defense Advanced Research Projects Agency"},{"id":"https://openalex.org/G848032724","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8851674072","display_name":null,"funder_award_id":"W911NF-17-C-0099","funder_id":"https://openalex.org/F4320332180","funder_display_name":"Defense Advanced Research Projects Agency"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"},{"id":"https://openalex.org/F4320332186","display_name":"Defense Threat Reduction Agency","ror":"https://ror.org/04tz64554"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3042602466.pdf","grobid_xml":"https://content.openalex.org/works/W3042602466.grobid-xml"},"referenced_works_count":16,"referenced_works":["https://openalex.org/W2048330531","https://openalex.org/W2067292826","https://openalex.org/W2106490775","https://openalex.org/W2122678284","https://openalex.org/W2153383412","https://openalex.org/W2238728730","https://openalex.org/W2250189634","https://openalex.org/W2593560537","https://openalex.org/W2890931111","https://openalex.org/W2964117810","https://openalex.org/W3003661976","https://openalex.org/W3004011066","https://openalex.org/W3004119480","https://openalex.org/W3081051539","https://openalex.org/W4231510805","https://openalex.org/W4233135949"],"related_works":[],"abstract_inverted_index":{"Mining":[0],"a":[1,8,78,86,98,107,112,120,130,167],"set":[2,99,169],"of":[3,100,138,170],"meaningful":[4],"topics":[5,172],"organized":[6],"into":[7,41],"hierarchy":[9,56],"is":[10],"intuitively":[11],"appealing":[12],"since":[13],"topic":[14,27,30,34,39,55,69],"correlations":[15],"are":[16],"ubiquitous":[17],"in":[18,148],"massive":[19],"text":[20,108,125,180],"corpora.":[21],"To":[22,65],"account":[23],"for":[24,103,152],"potential":[25],"hierarchical":[26,29,68,171,179],"structures,":[28],"models":[31,35],"generalize":[32],"flat":[33],"by":[36,90],"incorporating":[37],"latent":[38],"hierarchies":[40],"their":[42,49],"generative":[43,146],"modeling":[44,137],"process.":[45],"However,":[46],"due":[47],"to":[48,96,110],"purely":[50],"unsupervised":[51],"nature,":[52],"the":[53,67,139,144,149],"learned":[54],"often":[57],"deviates":[58],"from":[59,106],"users'":[60],"particular":[61],"needs":[62],"or":[63],"interests.":[64],"guide":[66],"discovery":[70],"process":[71,147],"with":[72,129,173],"minimal":[73],"user":[74,113],"supervision,":[75],"we":[76],"propose":[77],"new":[79],"task,":[80],"Hierarchical":[81],"Topic":[82],"Mining,":[83],"which":[84],"takes":[85],"category":[87,91,105,140],"tree":[88,123,141],"described":[89],"names":[92],"only,":[93],"and":[94,124,143,176],"aims":[95],"mine":[97],"representative":[101],"terms":[102],"each":[104],"corpus":[109,145],"help":[111],"comprehend":[114],"his/her":[115],"interested":[116],"topics.":[117],"We":[118],"develop":[119],"novel":[121],"joint":[122],"embedding":[126],"method":[127],"along":[128],"principled":[131],"optimization":[132],"procedure":[133],"that":[134,161],"allows":[135],"simultaneous":[136],"structure":[142],"spherical":[150],"space":[151],"effective":[153],"category-representative":[154],"term":[155],"discovery.":[156],"Our":[157],"comprehensive":[158],"experiments":[159],"show":[160],"our":[162],"model,":[163],"named":[164],"JoSH,":[165],"mines":[166],"high-quality":[168],"high":[174],"efficiency":[175],"benefits":[177],"weakly-supervised":[178],"classification":[181],"tasks.":[182]},"counts_by_year":[{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":18},{"year":2023,"cited_by_count":11},{"year":2022,"cited_by_count":10},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":3}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2020-07-23T00:00:00"}