{"id":"https://openalex.org/W1969351518","doi":"https://doi.org/10.1145/1165485.1165513","title":"Effective document clustering for large heterogeneous law firm collections","display_name":"Effective document clustering for large heterogeneous law firm collections","publication_year":2005,"publication_date":"2005-06-06","ids":{"openalex":"https://openalex.org/W1969351518","doi":"https://doi.org/10.1145/1165485.1165513","mag":"1969351518"},"language":"en","primary_location":{"id":"doi:10.1145/1165485.1165513","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1165485.1165513","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 10th international conference on Artificial intelligence and law","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://conservancy.umn.edu/bitstreams/f135e867-8a2b-47c1-8dbb-0bbee0f1768a/download","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5025701458","display_name":"Jack G. Conrad","orcid":"https://orcid.org/0000-0001-9114-9385"},"institutions":[{"id":"https://openalex.org/I68384125","display_name":"Thomson Reuters (United States)","ror":"https://ror.org/00m7gt169","country_code":"US","type":"company","lineage":["https://openalex.org/I68384125"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jack G. Conrad","raw_affiliation_strings":["Thomson Legal &amp; Regulatory, Minnesota"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Thomson Legal &amp; Regulatory, Minnesota","institution_ids":["https://openalex.org/I68384125"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011340349","display_name":"Khalid Al-Kofahi","orcid":null},"institutions":[{"id":"https://openalex.org/I68384125","display_name":"Thomson Reuters (United States)","ror":"https://ror.org/00m7gt169","country_code":"US","type":"company","lineage":["https://openalex.org/I68384125"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Khalid Al-Kofahi","raw_affiliation_strings":["Thomson Legal &amp; Regulatory, Minnesota"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Thomson Legal &amp; Regulatory, Minnesota","institution_ids":["https://openalex.org/I68384125"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101976139","display_name":"Ying Zhao","orcid":"https://orcid.org/0000-0001-6228-5433"},"institutions":[{"id":"https://openalex.org/I130238516","display_name":"University of Minnesota","ror":"https://ror.org/017zqws13","country_code":"US","type":"education","lineage":["https://openalex.org/I130238516"]},{"id":"https://openalex.org/I2800403580","display_name":"University of Minnesota System","ror":"https://ror.org/03grvy078","country_code":"US","type":"education","lineage":["https://openalex.org/I2800403580"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ying Zhao","raw_affiliation_strings":["University of Minnesota, Minneapolis, Minnesota"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Minnesota, Minneapolis, Minnesota","institution_ids":["https://openalex.org/I2800403580","https://openalex.org/I130238516"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5082384108","display_name":"George Karypis","orcid":"https://orcid.org/0000-0003-2753-1437"},"institutions":[{"id":"https://openalex.org/I130238516","display_name":"University of Minnesota","ror":"https://ror.org/017zqws13","country_code":"US","type":"education","lineage":["https://openalex.org/I130238516"]},{"id":"https://openalex.org/I2800403580","display_name":"University of Minnesota System","ror":"https://ror.org/03grvy078","country_code":"US","type":"education","lineage":["https://openalex.org/I2800403580"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"George Karypis","raw_affiliation_strings":["University of Minnesota, Minneapolis, Minnesota"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Minnesota, Minneapolis, Minnesota","institution_ids":["https://openalex.org/I2800403580","https://openalex.org/I130238516"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":7.6374,"has_fulltext":false,"cited_by_count":52,"citation_normalized_percentile":{"value":0.96633938,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"177","last_page":"187"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9904999732971191,"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"}},"topics":[{"id":"https://openalex.org/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9904999732971191,"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"}},{"id":"https://openalex.org/T13643","display_name":"Artificial Intelligence in Law","score":0.983299970626831,"subfield":{"id":"https://openalex.org/subfields/3320","display_name":"Political Science and International Relations"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.9729999899864197,"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":0.8445155620574951},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7580209970474243},{"id":"https://openalex.org/keywords/hierarchical-clustering","display_name":"Hierarchical clustering","score":0.585693895816803},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5280678272247314},{"id":"https://openalex.org/keywords/document-clustering","display_name":"Document clustering","score":0.5082192420959473},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.48464852571487427},{"id":"https://openalex.org/keywords/statute","display_name":"Statute","score":0.458956778049469},{"id":"https://openalex.org/keywords/brown-clustering","display_name":"Brown clustering","score":0.4561738967895508},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.39890506863594055},{"id":"https://openalex.org/keywords/fuzzy-clustering","display_name":"Fuzzy clustering","score":0.3973388075828552},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.35792163014411926},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.23465746641159058},{"id":"https://openalex.org/keywords/canopy-clustering-algorithm","display_name":"Canopy clustering algorithm","score":0.18573319911956787},{"id":"https://openalex.org/keywords/law","display_name":"Law","score":0.12878885865211487}],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.8445155620574951},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7580209970474243},{"id":"https://openalex.org/C92835128","wikidata":"https://www.wikidata.org/wiki/Q1277447","display_name":"Hierarchical clustering","level":3,"score":0.585693895816803},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5280678272247314},{"id":"https://openalex.org/C177937566","wikidata":"https://www.wikidata.org/wiki/Q4223102","display_name":"Document clustering","level":3,"score":0.5082192420959473},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.48464852571487427},{"id":"https://openalex.org/C17319257","wikidata":"https://www.wikidata.org/wiki/Q21189184","display_name":"Statute","level":2,"score":0.458956778049469},{"id":"https://openalex.org/C167984511","wikidata":"https://www.wikidata.org/wiki/Q17003931","display_name":"Brown clustering","level":5,"score":0.4561738967895508},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.39890506863594055},{"id":"https://openalex.org/C17212007","wikidata":"https://www.wikidata.org/wiki/Q5511111","display_name":"Fuzzy clustering","level":3,"score":0.3973388075828552},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.35792163014411926},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.23465746641159058},{"id":"https://openalex.org/C104047586","wikidata":"https://www.wikidata.org/wiki/Q5033439","display_name":"Canopy clustering algorithm","level":4,"score":0.18573319911956787},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.12878885865211487},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1145/1165485.1165513","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1165485.1165513","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 10th international conference on Artificial intelligence and law","raw_type":"proceedings-article"},{"id":"pmh:oai:conservancy.umn.edu:11299/215657","is_oa":true,"landing_page_url":"http://hdl.handle.net/11299/215657","pdf_url":"https://conservancy.umn.edu/bitstreams/f135e867-8a2b-47c1-8dbb-0bbee0f1768a/download","source":{"id":"https://openalex.org/S4306402521","display_name":"University of Minnesota Digital Conservancy (University of Minnesota)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I130238516","host_organization_name":"University of Minnesota","host_organization_lineage":["https://openalex.org/I130238516"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Report"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.156.1956","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.156.1956","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.conradweb.org/~jackg/pubs/ICAIL05p_Conrad-Zhao.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.96.723","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.96.723","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.umn.edu/tech_reports_upload/tr2005/05-016.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.97.9470","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.97.9470","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://glaros.dtc.umn.edu/gkhome/fetch/papers/edcICAIL05.pdf","raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:conservancy.umn.edu:11299/215657","is_oa":true,"landing_page_url":"http://hdl.handle.net/11299/215657","pdf_url":"https://conservancy.umn.edu/bitstreams/f135e867-8a2b-47c1-8dbb-0bbee0f1768a/download","source":{"id":"https://openalex.org/S4306402521","display_name":"University of Minnesota Digital Conservancy (University of Minnesota)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I130238516","host_organization_name":"University of Minnesota","host_organization_lineage":["https://openalex.org/I130238516"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Report"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.6899999976158142,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W1969351518.pdf"},"referenced_works_count":40,"referenced_works":["https://openalex.org/W34133297","https://openalex.org/W1495419098","https://openalex.org/W1524704912","https://openalex.org/W1651093245","https://openalex.org/W1833785989","https://openalex.org/W1937152602","https://openalex.org/W1971318281","https://openalex.org/W1971784203","https://openalex.org/W1993676235","https://openalex.org/W1996764654","https://openalex.org/W1997143441","https://openalex.org/W1999236014","https://openalex.org/W2026450968","https://openalex.org/W2035770827","https://openalex.org/W2036233989","https://openalex.org/W2039576845","https://openalex.org/W2057712948","https://openalex.org/W2087962968","https://openalex.org/W2098162425","https://openalex.org/W2113076747","https://openalex.org/W2116929951","https://openalex.org/W2117853077","https://openalex.org/W2119072456","https://openalex.org/W2120322324","https://openalex.org/W2124957865","https://openalex.org/W2127218421","https://openalex.org/W2131687179","https://openalex.org/W2134149556","https://openalex.org/W2136052850","https://openalex.org/W2151735738","https://openalex.org/W2319660501","https://openalex.org/W2799061466","https://openalex.org/W3216379332","https://openalex.org/W4230946174","https://openalex.org/W4241122026","https://openalex.org/W4388147587","https://openalex.org/W6601394625","https://openalex.org/W6770641979","https://openalex.org/W6806421124","https://openalex.org/W7037644959"],"related_works":["https://openalex.org/W4292477917","https://openalex.org/W2034251629","https://openalex.org/W4234578264","https://openalex.org/W4237492828","https://openalex.org/W2130194910","https://openalex.org/W2189374779","https://openalex.org/W2605148547","https://openalex.org/W4231226332","https://openalex.org/W2049508213","https://openalex.org/W2378900857"],"abstract_inverted_index":{"Computational":[0],"resources":[1],"for":[2,55,216],"research":[3],"in":[4,35,60,68,188,208],"legal":[5,16,78,200],"environments":[6],"have":[7,119],"historically":[8],"implied":[9],"remote":[10],"access":[11],"to":[12,106,112,144,199],"large":[13],"databases":[14],"of":[15,97,122,150,153,161,190,214],"documents":[17,133],"such":[18,203],"as":[19,134,136,174,176],"case":[20],"law,":[21],"statutes,":[22],"law":[23,45,132,138],"reviews":[24],"and":[25,64,71,109,130,148,193,197],"administrative":[26],"materials.":[27],"Today,":[28],"by":[29,219],"contrast,":[30],"there":[31],"exists":[32],"enormous":[33],"growth":[34,50],"lawyers'":[36],"electronic":[37],"work":[38],"product":[39],"within":[40,44],"these":[41,98,182],"environments,":[42],"specifically":[43],"firms.":[46],"Along":[47],"with":[48,83],"this":[49,66,115],"has":[51],"come":[52],"the":[53,95,146,159,209],"need":[54],"accelerated":[56],"knowledge":[57],"management---automated":[58],"assistance":[59],"organizing,":[61],"analyzing,":[62],"retrieving":[63],"presenting":[65],"content":[67],"a":[69,76,151],"useful":[70,198],"distributed":[72],"manner.In":[73],"cases":[74],"where":[75],"relevant":[77],"taxonomy":[79],"is":[80],"available,":[81],"together":[82],"representative":[84],"labeled":[85],"data,":[86],"automated":[87],"text":[88],"classification":[89,220],"tools":[90],"can":[91,205],"be":[92],"applied.":[93],"In":[94],"absence":[96],"resources,":[99],"document":[100],"clustering":[101,126,155,165,170,184],"offers":[102],"an":[103,110],"alternative":[104],"approach":[105,116],"organizing":[107],"collections,":[108],"adjunct":[111],"search.To":[113],"explore":[114],"further,":[117],"we":[118,167],"conducted":[120],"sets":[121],"successively":[123],"more":[124],"complex":[125],"experiments":[127],"using":[128],"primary":[129],"secondary":[131],"well":[135,175],"actual":[137],"firm":[139],"data.":[140],"Tests":[141],"were":[142],"run":[143],"determine":[145],"efficiency":[147],"effectiveness":[149],"number":[152],"essential":[154],"functions.":[156],"After":[157],"examining":[158],"performance":[160],"traditional":[162],"or":[163,211],"hard":[164],"applications,":[166],"investigate":[168],"soft":[169],"(multiple":[171],"cluster":[172],"assignments)":[173],"hierarchical":[177],"clustering.":[178],"We":[179],"show":[180],"how":[181],"latter":[183],"approaches":[185],"are":[186],"effective,":[187],"terms":[189],"both":[191],"internal":[192],"external":[194],"quality":[195],"measures,":[196],"researchers.":[201],"Moreover,":[202],"techniques":[204],"ultimately":[206],"assist":[207],"automatic":[210],"semi-automatic":[212],"generation":[213],"taxonomies":[215],"subsequent":[217],"use":[218],"programs.":[221]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2021,"cited_by_count":8},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":4},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":6},{"year":2012,"cited_by_count":1}],"updated_date":"2026-07-03T08:13:44.112507","created_date":"2025-10-10T00:00:00"}
