{"id":"https://openalex.org/W2167029568","doi":"https://doi.org/10.14778/1687627.1687673","title":"Mining document collections to facilitate accurate approximate entity matching","display_name":"Mining document collections to facilitate accurate approximate entity matching","publication_year":2009,"publication_date":"2009-08-01","ids":{"openalex":"https://openalex.org/W2167029568","doi":"https://doi.org/10.14778/1687627.1687673","mag":"2167029568"},"language":"en","primary_location":{"id":"doi:10.14778/1687627.1687673","is_oa":false,"landing_page_url":"https://doi.org/10.14778/1687627.1687673","pdf_url":null,"source":{"id":"https://openalex.org/S4210226185","display_name":"Proceedings of the VLDB Endowment","issn_l":"2150-8097","issn":["2150-8097"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the VLDB Endowment","raw_type":"journal-article"},"type":"article","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/A5038037154","display_name":"Surajit Chaudhuri","orcid":"https://orcid.org/0000-0001-8252-5270"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Surajit Chaudhuri","raw_affiliation_strings":["Microsoft Research, Redmond, WA"],"affiliations":[{"raw_affiliation_string":"Microsoft Research, Redmond, WA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Venkatesh Ganti","orcid":null},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Venkatesh Ganti","raw_affiliation_strings":["Microsoft Research, Redmond, WA"],"affiliations":[{"raw_affiliation_string":"Microsoft Research, Redmond, WA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101406351","display_name":"Dong Xin","orcid":"https://orcid.org/0000-0002-1414-9354"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dong Xin","raw_affiliation_strings":["Microsoft Research, Redmond, WA"],"affiliations":[{"raw_affiliation_string":"Microsoft Research, Redmond, WA","institution_ids":["https://openalex.org/I1290206253"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5038037154"],"corresponding_institution_ids":["https://openalex.org/I1290206253"],"apc_list":null,"apc_paid":null,"fwci":5.0004,"has_fulltext":false,"cited_by_count":38,"citation_normalized_percentile":{"value":0.95186602,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"2","issue":"1","first_page":"395","last_page":"406"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9973000288009644,"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/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9962999820709229,"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/substring","display_name":"Substring","score":0.9422932863235474},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8440470695495605},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6241074204444885},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.5930705666542053},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5702191591262817},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.56939697265625},{"id":"https://openalex.org/keywords/string-metric","display_name":"String metric","score":0.5462725162506104},{"id":"https://openalex.org/keywords/string","display_name":"String (physics)","score":0.5365047454833984},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5164240002632141},{"id":"https://openalex.org/keywords/string-searching-algorithm","display_name":"String searching algorithm","score":0.47753632068634033},{"id":"https://openalex.org/keywords/table","display_name":"Table (database)","score":0.44898679852485657},{"id":"https://openalex.org/keywords/pattern-matching","display_name":"Pattern matching","score":0.27862679958343506},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.2714632749557495},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2353971302509308},{"id":"https://openalex.org/keywords/data-structure","display_name":"Data structure","score":0.19356757402420044},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10085996985435486}],"concepts":[{"id":"https://openalex.org/C182407805","wikidata":"https://www.wikidata.org/wiki/Q2626534","display_name":"Substring","level":3,"score":0.9422932863235474},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8440470695495605},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6241074204444885},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.5930705666542053},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5702191591262817},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.56939697265625},{"id":"https://openalex.org/C22820288","wikidata":"https://www.wikidata.org/wiki/Q9050568","display_name":"String metric","level":4,"score":0.5462725162506104},{"id":"https://openalex.org/C157486923","wikidata":"https://www.wikidata.org/wiki/Q1376436","display_name":"String (physics)","level":2,"score":0.5365047454833984},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5164240002632141},{"id":"https://openalex.org/C7757238","wikidata":"https://www.wikidata.org/wiki/Q374040","display_name":"String searching algorithm","level":3,"score":0.47753632068634033},{"id":"https://openalex.org/C45235069","wikidata":"https://www.wikidata.org/wiki/Q278425","display_name":"Table (database)","level":2,"score":0.44898679852485657},{"id":"https://openalex.org/C68859911","wikidata":"https://www.wikidata.org/wiki/Q1503724","display_name":"Pattern matching","level":2,"score":0.27862679958343506},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.2714632749557495},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2353971302509308},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.19356757402420044},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10085996985435486},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"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/C37914503","wikidata":"https://www.wikidata.org/wiki/Q156495","display_name":"Mathematical physics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.14778/1687627.1687673","is_oa":false,"landing_page_url":"https://doi.org/10.14778/1687627.1687673","pdf_url":null,"source":{"id":"https://openalex.org/S4210226185","display_name":"Proceedings of the VLDB Endowment","issn_l":"2150-8097","issn":["2150-8097"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the VLDB Endowment","raw_type":"journal-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.151.4358","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.151.4358","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.vldb.org/pvldb/2/vldb09-315.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W167149422","https://openalex.org/W1567365482","https://openalex.org/W1574901103","https://openalex.org/W2007682403","https://openalex.org/W2037594241","https://openalex.org/W2046020929","https://openalex.org/W2048468185","https://openalex.org/W2064853889","https://openalex.org/W2072173758","https://openalex.org/W2096071381","https://openalex.org/W2098165490","https://openalex.org/W2098571654","https://openalex.org/W2099964107","https://openalex.org/W2113618143","https://openalex.org/W2119400430","https://openalex.org/W2121516976","https://openalex.org/W2147880316","https://openalex.org/W2159491434","https://openalex.org/W2166776180","https://openalex.org/W2167181946","https://openalex.org/W2173213060","https://openalex.org/W4252403066","https://openalex.org/W6634133269"],"related_works":["https://openalex.org/W2298204719","https://openalex.org/W152351265","https://openalex.org/W52396946","https://openalex.org/W3042295250","https://openalex.org/W2549495077","https://openalex.org/W2748704845","https://openalex.org/W1564013439","https://openalex.org/W2119057313","https://openalex.org/W3112977702","https://openalex.org/W4230921427"],"abstract_inverted_index":{"Many":[0],"entity":[1,7,16,28,113],"extraction":[2],"techniques":[3,98],"leverage":[4],"large":[5,62],"reference":[6,27,46,58,112,132,143],"tables":[8],"to":[9,68,99,135],"identify":[10],"entities":[11,59,133],"in":[12,19,25],"documents.":[13],"Often,":[14],"an":[15,81,128,151],"is":[17],"referenced":[18],"document":[20,106],"collections":[21,107],"differently":[22],"from":[23],"that":[24,136],"the":[26,33,52,123,141,157],"tables.":[29],"Therefore,":[30],"we":[31,90,155],"study":[32],"problem":[34,124],"of":[35,64,117,119,125,137,161],"determining":[36],"whether":[37],"or":[38],"not":[39],"a":[40,45,61,92,110],"substring":[41],"\"approximately\"":[42],"matches":[43],"with":[44,115],"entity.":[47],"Similarity":[48],"measures":[49],"which":[50,145],"exploit":[51],"correlation":[53],"between":[54],"candidate":[55],"substrings":[56],"and":[57,95,108,159],"across":[60],"number":[63],"documents":[65],"are":[66],"known":[67],"be":[69,147],"more":[70],"robust":[71],"than":[72],"traditional":[73],"stand":[74],"alone":[75],"string-based":[76],"similarity":[77],"functions.":[78],"However,":[79],"such":[80],"approach":[82],"has":[83],"significant":[84],"efficiency":[85,102],"challenges.":[86,103],"In":[87,150],"this":[88],"paper,":[89],"adopt":[91],"new":[93,97],"architecture":[94],"propose":[96],"address":[100],"these":[101],"We":[104],"mine":[105],"expand":[109],"given":[111],"table":[114],"variations":[116],"each":[118],"its":[120],"entities.":[121],"Thus,":[122],"approximately":[126],"matching":[127],"input":[129],"string":[130],"against":[131,140],"reduces":[134],"exact":[138],"match":[139],"expanded":[142],"table,":[144],"can":[146],"implemented":[148],"efficiently.":[149],"extensive":[152],"experimental":[153],"evaluation,":[154],"demonstrate":[156],"accuracy":[158],"scalability":[160],"our":[162],"techniques.":[163]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":9},{"year":2013,"cited_by_count":7},{"year":2012,"cited_by_count":4}],"updated_date":"2026-04-17T18:11:37.981687","created_date":"2025-10-10T00:00:00"}