{"id":"https://openalex.org/W55381671","doi":"https://doi.org/10.1137/1.9781611972771.11","title":"Active Learning of Constraints for Semi-supervised Text Clustering","display_name":"Active Learning of Constraints for Semi-supervised Text Clustering","publication_year":2007,"publication_date":"2007-04-26","ids":{"openalex":"https://openalex.org/W55381671","doi":"https://doi.org/10.1137/1.9781611972771.11","mag":"55381671"},"language":"en","primary_location":{"id":"doi:10.1137/1.9781611972771.11","doi":"https://doi.org/10.1137/1.9781611972771.11","is_oa":true,"landing_page_url":"https://doi.org/10.1137/1.9781611972771.11","pdf_url":"https://epubs.siam.org/doi/pdf/10.1137/1.9781611972771.11","source":{"id":"https://openalex.org/S4306420871","display_name":"SIAM International Conference on Data Mining","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2007 SIAM International Conference on Data Mining","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://epubs.siam.org/doi/pdf/10.1137/1.9781611972771.11","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5044103045","display_name":"Ruizhang Huang","orcid":"https://orcid.org/0000-0002-8941-3914","observed_orcids":["https://orcid.org/0000-0002-8941-3914"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ruizhang Huang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018582154","display_name":"Wai Pang Lam","orcid":"https://orcid.org/0000-0001-5479-377X","observed_orcids":["https://orcid.org/0000-0001-5479-377X"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wai Lam","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5100374007","display_name":"Zhigang Zhang","orcid":"https://orcid.org/0009-0006-1093-1855","observed_orcids":["https://orcid.org/0009-0006-1093-1855"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhigang Zhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.9474,"has_fulltext":true,"cited_by_count":20,"citation_normalized_percentile":{"value":0.69736136,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"113","last_page":"124"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12072","display_name":"Machine Learning and Algorithms","score":0.6851000189781189,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.6851000189781189,"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/T10637","display_name":"Advanced Clustering Algorithms Research","score":0.28999999165534973,"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":0.007300000172108412,"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/active-learning-machine-learning","display_name":"active learning (machine learning)","score":0.8960000276565552},{"id":"https://openalex.org/keywords/constraint-learning","display_name":"constraint learning","score":0.6809999942779541},{"id":"https://openalex.org/keywords/semi-supervised-clustering","display_name":"semi-supervised clustering","score":0.8169999718666077},{"id":"https://openalex.org/keywords/document-clustering","display_name":"document clustering","score":0.906000018119812},{"id":"https://openalex.org/keywords/gain-function","display_name":"gain function","score":0.7900000214576721},{"id":"https://openalex.org/keywords/user-judgment","display_name":"user judgment","score":0.652999997138977}],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.8217382431030273},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7034133672714233},{"id":"https://openalex.org/C2983203078","wikidata":"https://www.wikidata.org/wiki/Q255166","display_name":"Information gain","level":2,"score":0.6723516583442688},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.6041530966758728},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.5989649891853333},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5941351056098938},{"id":"https://openalex.org/C177937566","wikidata":"https://www.wikidata.org/wiki/Q4223102","display_name":"Document clustering","level":3,"score":0.5838631987571716},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.5036265254020691},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4834223985671997},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3806465268135071},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3334381580352783},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10565236210823059},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1137/1.9781611972771.11","doi":"https://doi.org/10.1137/1.9781611972771.11","is_oa":true,"landing_page_url":"https://doi.org/10.1137/1.9781611972771.11","pdf_url":"https://epubs.siam.org/doi/pdf/10.1137/1.9781611972771.11","source":{"id":"https://openalex.org/S4306420871","display_name":"SIAM International Conference on Data Mining","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2007 SIAM International Conference on Data Mining","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1137/1.9781611972771.11","doi":"https://doi.org/10.1137/1.9781611972771.11","is_oa":true,"landing_page_url":"https://doi.org/10.1137/1.9781611972771.11","pdf_url":"https://epubs.siam.org/doi/pdf/10.1137/1.9781611972771.11","source":{"id":"https://openalex.org/S4306420871","display_name":"SIAM International Conference on Data Mining","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2007 SIAM International Conference on Data Mining","raw_type":"proceedings-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W55381671.pdf","grobid_xml":"https://content.openalex.org/works/W55381671.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2162009590","https://openalex.org/W2418496578","https://openalex.org/W2077775960","https://openalex.org/W2126822170","https://openalex.org/W1974121224","https://openalex.org/W1965450189","https://openalex.org/W568753462","https://openalex.org/W2386249431","https://openalex.org/W2153839362","https://openalex.org/W7096011381"],"abstract_inverted_index":{"This":[0,49],"paper":[1],"investigates":[2],"active":[3],"learning":[4],"of":[5,14,62,93,99,103,128,169],"constraints":[6],"for":[7,25,29,37,125,174,189],"semi-supervised":[8,132],"document":[9,22,42,64,95,105,129,137,170],"clustering.":[10],"We":[11,146],"make":[12],"use":[13],"the":[15,21,39,45,60,63,79,86,91,101,122,159,164,176],"intermediate":[16,160],"clustering":[17,133,161,177],"results":[18,156],"to":[19,116,184],"guide":[20],"pair":[23,96,138],"selection":[24,119,139],"obtaining":[26],"user":[27],"judgments":[28],"constraint":[30],"generation.":[31],"A":[32],"gain":[33,50,72,76,81,109,123,135],"function":[34,51],"is":[35,97,181],"designed":[36],"choosing":[38],"most":[40],"informative":[41],"pairs":[43,171],"given":[44],"current":[46],"cluster":[47],"assignments.":[48],"measures":[52],"how":[53],"much":[54],"we":[55,83],"can":[56],"learn":[57],"by":[58,89],"revealing":[59,90,100],"judgment":[61,92,102],"pairs.":[65,106,130],"Two":[66],"methods":[67],"are":[68,140,172],"investigated,":[69],"namely,":[70],"independent":[71,80,98],"model":[73,110],"and":[74,120,134,163],"dependent":[75,108],"model.":[77],"In":[78],"model,":[82],"assume":[84],"that":[85,158],"information":[87],"learned":[88],"a":[94,126,167,185],"other":[104],"The":[107,155],"also":[111,182],"considers":[112],"previously":[113],"chosen":[114],"documents":[115],"avoid":[117],"redundant":[118],"maximize":[121],"collectively":[124],"set":[127,168],"Constrained":[131],"directed":[136],"conducted":[141,148],"in":[142],"an":[143],"iterative":[144],"manner.":[145],"have":[147],"extensive":[149],"experiments":[150],"on":[151],"several":[152],"real-world":[153],"corpora.":[154],"demonstrate":[157],"assignments":[162],"interactions":[165],"among":[166],"useful":[173],"improving":[175],"performance.":[178],"Our":[179],"approach":[180],"superior":[183],"recent":[186],"existing":[187],"work":[188],"this":[190],"problem.":[191]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":5},{"year":2012,"cited_by_count":3}],"updated_date":"2026-10-05T09:50:58.205359","created_date":"2016-06-24T00:00:00"}