{"id":"https://openalex.org/W2139317750","doi":"https://doi.org/10.1145/2063576.2063689","title":"Transferring topical knowledge from auxiliary long texts for short text clustering","display_name":"Transferring topical knowledge from auxiliary long texts for short text clustering","publication_year":2011,"publication_date":"2011-10-24","ids":{"openalex":"https://openalex.org/W2139317750","doi":"https://doi.org/10.1145/2063576.2063689","mag":"2139317750"},"language":"en","primary_location":{"id":"doi:10.1145/2063576.2063689","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2063576.2063689","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 20th ACM international conference on Information and knowledge management","raw_type":"proceedings-article"},"type":"conference-paper","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/A5111776207","display_name":"Ou Jin","orcid":null},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ou Jin","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China","[Shanghai Jiao Tong University, Shanghai, China]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"[Shanghai Jiao Tong University, Shanghai, China]","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007393839","display_name":"Nathan N. Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Nathan N. Liu","raw_affiliation_strings":["Hong Kong University of Science and Technology, Hong Kong, Hong Kong","Hong Kong University Of Science And Technology, Hong Kong, Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hong Kong University of Science and Technology, Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I200769079"]},{"raw_affiliation_string":"Hong Kong University Of Science And Technology, Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012251323","display_name":"Kai Zhao","orcid":"https://orcid.org/0000-0002-5159-2312"},"institutions":[{"id":"https://openalex.org/I4210149379","display_name":"NEC (China)","ror":"https://ror.org/04xrcx824","country_code":"CN","type":"company","lineage":["https://openalex.org/I118347220","https://openalex.org/I4210149379"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kai Zhao","raw_affiliation_strings":["NEC Labs China, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NEC Labs China, Beijing, China","institution_ids":["https://openalex.org/I4210149379"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001571390","display_name":"Yong Yu","orcid":"https://orcid.org/0000-0003-0281-8271"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yong Yu","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China","[Shanghai Jiao Tong University, Shanghai, China]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"[Shanghai Jiao Tong University, Shanghai, China]","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100636286","display_name":"Qiang Yang","orcid":"https://orcid.org/0000-0001-5059-8360"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Qiang Yang","raw_affiliation_strings":["Hong Kong University of Science and Technology, Hong Kong, Hong Kong","Hong Kong University Of Science And Technology, Hong Kong, Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hong Kong University of Science and Technology, Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I200769079"]},{"raw_affiliation_string":"Hong Kong University Of Science And Technology, Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I200769079"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":224,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"775","last_page":"784"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9988999962806702,"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":0.9988999962806702,"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":0.998199999332428,"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/T13274","display_name":"Expert finding and Q&A systems","score":0.9972000122070312,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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":0.8186654448509216},{"id":"https://openalex.org/keywords/latent-dirichlet-allocation","display_name":"Latent Dirichlet allocation","score":0.7566119432449341},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.7245222330093384},{"id":"https://openalex.org/keywords/topic-model","display_name":"Topic model","score":0.5467617511749268},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5252097249031067},{"id":"https://openalex.org/keywords/noisy-text-analytics","display_name":"Noisy text analytics","score":0.5240257382392883},{"id":"https://openalex.org/keywords/document-clustering","display_name":"Document clustering","score":0.5026671886444092},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4929678440093994},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41340476274490356},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.37095481157302856},{"id":"https://openalex.org/keywords/text-mining","display_name":"Text mining","score":0.31497764587402344},{"id":"https://openalex.org/keywords/text-graph","display_name":"Text graph","score":0.1604299545288086}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8186654448509216},{"id":"https://openalex.org/C500882744","wikidata":"https://www.wikidata.org/wiki/Q269236","display_name":"Latent Dirichlet allocation","level":3,"score":0.7566119432449341},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.7245222330093384},{"id":"https://openalex.org/C171686336","wikidata":"https://www.wikidata.org/wiki/Q3532085","display_name":"Topic model","level":2,"score":0.5467617511749268},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5252097249031067},{"id":"https://openalex.org/C151375590","wikidata":"https://www.wikidata.org/wiki/Q17147076","display_name":"Noisy text analytics","level":4,"score":0.5240257382392883},{"id":"https://openalex.org/C177937566","wikidata":"https://www.wikidata.org/wiki/Q4223102","display_name":"Document clustering","level":3,"score":0.5026671886444092},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4929678440093994},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41340476274490356},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.37095481157302856},{"id":"https://openalex.org/C71472368","wikidata":"https://www.wikidata.org/wiki/Q676880","display_name":"Text mining","level":2,"score":0.31497764587402344},{"id":"https://openalex.org/C66945725","wikidata":"https://www.wikidata.org/wiki/Q18388823","display_name":"Text graph","level":3,"score":0.1604299545288086},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1145/2063576.2063689","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2063576.2063689","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 20th ACM international conference on Information and knowledge management","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.226.3331","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.226.3331","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://dollar.biz.uiowa.edu/%7Estreet/jin11.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.227.4848","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.227.4848","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cse.ust.hk/%7Eqyang/Docs/2011/cikm-short-text2.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.363.4560","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.363.4560","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cse.ust.hk/~qyang/Docs/2011/cikm-short-text.pdf","raw_type":"text"},{"id":"pmh:oai:repository.hkust.edu.hk:1783.1-35161","is_oa":false,"landing_page_url":"http://repository.hkust.edu.hk/ir/Record/1783.1-35161","pdf_url":null,"source":{"id":"https://openalex.org/S4306401796","display_name":"Rare & Special e-Zone (The Hong Kong University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I200769079","host_organization_name":"Hong Kong University of Science and Technology","host_organization_lineage":["https://openalex.org/I200769079"],"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":"Conference paper"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6399999856948853,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W1566018662","https://openalex.org/W1573190978","https://openalex.org/W1969486090","https://openalex.org/W1970544520","https://openalex.org/W1980995378","https://openalex.org/W1993972863","https://openalex.org/W2001082470","https://openalex.org/W2051224630","https://openalex.org/W2053968437","https://openalex.org/W2055400882","https://openalex.org/W2063904635","https://openalex.org/W2068463433","https://openalex.org/W2115575686","https://openalex.org/W2122683976","https://openalex.org/W2122922389","https://openalex.org/W2137958601","https://openalex.org/W2161443453","https://openalex.org/W2165698076","https://openalex.org/W2165744911","https://openalex.org/W2169821025","https://openalex.org/W2171836785","https://openalex.org/W2593831809","https://openalex.org/W6634191187","https://openalex.org/W6680441624"],"related_works":["https://openalex.org/W2769501189","https://openalex.org/W4315588616","https://openalex.org/W4312773271","https://openalex.org/W2888805565","https://openalex.org/W2962686197","https://openalex.org/W3005513013","https://openalex.org/W2207653751","https://openalex.org/W2611137333","https://openalex.org/W4309228610","https://openalex.org/W4294597112"],"abstract_inverted_index":{"With":[0],"the":[1,14,44,52,79,84,131,137,144,149,184,190],"rapid":[2],"growth":[3],"of":[4,16,43,54,128,175],"social":[5],"Web":[6],"applications":[7],"such":[8],"as":[9,78],"Twitter":[10,206],"and":[11,23,133,139,142,154,179,182,205],"online":[12],"advertisements,":[13],"task":[15],"understanding":[17],"short":[18,39,59,86,99,120,178,220],"texts":[19,87,181],"is":[20,65],"becoming":[21],"more":[22,24],"important.":[25],"Most":[26],"traditional":[27],"text":[28,36,40,55,100,108,121,221],"mining":[29,83],"techniques":[30,46,217],"are":[31,47],"designed":[32],"to":[33,51,68,97,187],"handle":[34],"long":[35,72,107,125,180],"documents.":[37,222],"For":[38],"messages,":[41,60],"many":[42],"existing":[45],"not":[48],"effective":[49],"due":[50],"sparseness":[53],"representations.":[56],"To":[57,147],"understand":[58],"we":[61,92,157,209],"observe":[62],"that":[63,112,118,208],"it":[64],"often":[66],"possible":[67,150],"find":[69],"topically":[70],"related":[71,124],"texts,":[73,126],"which":[74,170],"can":[75,210],"be":[76],"utilized":[77],"auxiliary":[80,106,140],"data":[81,141,194,207],"when":[82],"target":[85,138,155],"data.":[88,109],"In":[89],"this":[90],"article,":[91],"present":[93],"a":[94,159],"novel":[95,160],"approach":[96],"cluster":[98],"messages":[101],"via":[102],"transfer":[103],"learning":[104],"from":[105],"We":[110,196],"show":[111],"while":[113],"some":[114],"previous":[115],"work":[116],"exists":[117],"enhance":[119],"clustering":[122,145,200,219],"with":[123,189],"most":[127],"them":[129],"ignore":[130],"semantic":[132],"topical":[134],"inconsistencies":[135],"between":[136,152,193],"hurt":[143],"performance.":[146],"accommodate":[148],"inconsistency":[151,192],"source":[153],"data,":[156],"propose":[158],"topic":[161,185],"model":[162],"-":[163],"Dual":[164],"Latent":[165],"Dirichlet":[166],"Allocation":[167],"(DLDA)":[168],"model,":[169],"jointly":[171],"learns":[172],"two":[173],"sets":[174],"topics":[176],"on":[177,202],"couples":[183],"parameters":[186],"cope":[188],"potential":[191],"sets.":[195],"demonstrate":[197],"through":[198],"large-scale":[199],"experiments":[201],"both":[203],"advertisements":[204],"obtain":[211],"superior":[212],"performance":[213],"over":[214],"several":[215],"state-of-art":[216],"for":[218]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":11},{"year":2021,"cited_by_count":18},{"year":2020,"cited_by_count":22},{"year":2019,"cited_by_count":22},{"year":2018,"cited_by_count":26},{"year":2017,"cited_by_count":25},{"year":2016,"cited_by_count":20},{"year":2015,"cited_by_count":21},{"year":2014,"cited_by_count":14},{"year":2013,"cited_by_count":20},{"year":2012,"cited_by_count":9}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}