{"id":"https://openalex.org/W2010916971","doi":"https://doi.org/10.1145/1132863.1132868","title":"Integrating XML data sources using approximate joins","display_name":"Integrating XML data sources using approximate joins","publication_year":2006,"publication_date":"2006-03-01","ids":{"openalex":"https://openalex.org/W2010916971","doi":"https://doi.org/10.1145/1132863.1132868","mag":"2010916971"},"language":"en","primary_location":{"id":"doi:10.1145/1132863.1132868","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1132863.1132868","pdf_url":null,"source":{"id":"https://openalex.org/S90119964","display_name":"ACM Transactions on Database Systems","issn_l":"0362-5915","issn":["0362-5915","1557-4644"],"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":"ACM Transactions on Database Systems","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/A5114008024","display_name":"Sudipto Guha","orcid":null},"institutions":[{"id":"https://openalex.org/I36788626","display_name":"California University of Pennsylvania","ror":"https://ror.org/01spssf70","country_code":"US","type":"education","lineage":["https://openalex.org/I36788626"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Sudipto Guha","raw_affiliation_strings":["University of Pennsylvania","#N# * University of Pennsylvania"],"affiliations":[{"raw_affiliation_string":"University of Pennsylvania","institution_ids":["https://openalex.org/I36788626"]},{"raw_affiliation_string":"#N# * University of Pennsylvania","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087012731","display_name":"H. V. Jagadish","orcid":null},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan\u2013Ann Arbor","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"H. V. Jagadish","raw_affiliation_strings":["University of Michigan","(University of Michigan)"],"affiliations":[{"raw_affiliation_string":"University of Michigan","institution_ids":["https://openalex.org/I27837315"]},{"raw_affiliation_string":"(University of Michigan)","institution_ids":["https://openalex.org/I27837315"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035257754","display_name":"Nick Koudas","orcid":"https://orcid.org/0000-0001-5648-0638"},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Nick Koudas","raw_affiliation_strings":["University of Toronto"],"affiliations":[{"raw_affiliation_string":"University of Toronto","institution_ids":["https://openalex.org/I185261750"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088315797","display_name":"Divesh Srivastava","orcid":"https://orcid.org/0000-0002-7609-9217"},"institutions":[{"id":"https://openalex.org/I1283103587","display_name":"AT&T (United States)","ror":"https://ror.org/02bbd5539","country_code":"US","type":"company","lineage":["https://openalex.org/I1283103587"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Divesh Srivastava","raw_affiliation_strings":["AT&T Labs--Research"],"affiliations":[{"raw_affiliation_string":"AT&T Labs--Research","institution_ids":["https://openalex.org/I1283103587"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101948685","display_name":"Ting Yu","orcid":"https://orcid.org/0000-0002-7054-5773"},"institutions":[{"id":"https://openalex.org/I137902535","display_name":"North Carolina State University","ror":"https://ror.org/04tj63d06","country_code":"US","type":"education","lineage":["https://openalex.org/I137902535"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ting Yu","raw_affiliation_strings":["North Carolina State University","North Carolina State University,"],"affiliations":[{"raw_affiliation_string":"North Carolina State University","institution_ids":["https://openalex.org/I137902535"]},{"raw_affiliation_string":"North Carolina State University,","institution_ids":["https://openalex.org/I137902535"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5114008024"],"corresponding_institution_ids":["https://openalex.org/I36788626"],"apc_list":null,"apc_paid":null,"fwci":3.2241,"has_fulltext":false,"cited_by_count":28,"citation_normalized_percentile":{"value":0.91643616,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"31","issue":"1","first_page":"161","last_page":"207"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11106","display_name":"Data Management and Algorithms","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T11106","display_name":"Data Management and Algorithms","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T10317","display_name":"Advanced Database Systems and Queries","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T11269","display_name":"Algorithms and Data Compression","score":0.995199978351593,"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/computer-science","display_name":"Computer science","score":0.8795677423477173},{"id":"https://openalex.org/keywords/joins","display_name":"Joins","score":0.7643133401870728},{"id":"https://openalex.org/keywords/xml-validation","display_name":"XML validation","score":0.6663409471511841},{"id":"https://openalex.org/keywords/xml","display_name":"XML","score":0.6552714109420776},{"id":"https://openalex.org/keywords/efficient-xml-interchange","display_name":"Efficient XML Interchange","score":0.6136469841003418},{"id":"https://openalex.org/keywords/document-structure-description","display_name":"Document Structure Description","score":0.5465168952941895},{"id":"https://openalex.org/keywords/xml-schema","display_name":"XML Schema (W3C)","score":0.5137404203414917},{"id":"https://openalex.org/keywords/xml-database","display_name":"XML database","score":0.5084063410758972},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.507733941078186},{"id":"https://openalex.org/keywords/streaming-xml","display_name":"Streaming XML","score":0.48256057500839233},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4688452482223511},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4627532958984375},{"id":"https://openalex.org/keywords/tree","display_name":"Tree (set theory)","score":0.4432090222835541},{"id":"https://openalex.org/keywords/xml-encryption","display_name":"XML Encryption","score":0.3985552489757538},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.38535749912261963},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.175052672624588},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.14087823033332825}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8795677423477173},{"id":"https://openalex.org/C2778692605","wikidata":"https://www.wikidata.org/wiki/Q4041866","display_name":"Joins","level":2,"score":0.7643133401870728},{"id":"https://openalex.org/C55348073","wikidata":"https://www.wikidata.org/wiki/Q595926","display_name":"XML validation","level":3,"score":0.6663409471511841},{"id":"https://openalex.org/C8797682","wikidata":"https://www.wikidata.org/wiki/Q2115","display_name":"XML","level":2,"score":0.6552714109420776},{"id":"https://openalex.org/C11508877","wikidata":"https://www.wikidata.org/wiki/Q1124477","display_name":"Efficient XML Interchange","level":3,"score":0.6136469841003418},{"id":"https://openalex.org/C68699486","wikidata":"https://www.wikidata.org/wiki/Q265904","display_name":"Document Structure Description","level":3,"score":0.5465168952941895},{"id":"https://openalex.org/C40713593","wikidata":"https://www.wikidata.org/wiki/Q16342","display_name":"XML Schema (W3C)","level":5,"score":0.5137404203414917},{"id":"https://openalex.org/C183068750","wikidata":"https://www.wikidata.org/wiki/Q357393","display_name":"XML database","level":3,"score":0.5084063410758972},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.507733941078186},{"id":"https://openalex.org/C44883583","wikidata":"https://www.wikidata.org/wiki/Q7622687","display_name":"Streaming XML","level":3,"score":0.48256057500839233},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4688452482223511},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4627532958984375},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.4432090222835541},{"id":"https://openalex.org/C173242113","wikidata":"https://www.wikidata.org/wiki/Q607488","display_name":"XML Encryption","level":4,"score":0.3985552489757538},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.38535749912261963},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.175052672624588},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.14087823033332825},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/1132863.1132868","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1132863.1132868","pdf_url":null,"source":{"id":"https://openalex.org/S90119964","display_name":"ACM Transactions on Database Systems","issn_l":"0362-5915","issn":["0362-5915","1557-4644"],"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":"ACM Transactions on Database Systems","raw_type":"journal-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.141.549","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.141.549","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.csc.ncsu.edu/faculty/yu/pubs/xml-approxjoin-tods06.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":44,"referenced_works":["https://openalex.org/W9273873","https://openalex.org/W91532282","https://openalex.org/W93804029","https://openalex.org/W178414959","https://openalex.org/W938539187","https://openalex.org/W1485156179","https://openalex.org/W1501400124","https://openalex.org/W1516516841","https://openalex.org/W1533573623","https://openalex.org/W1633157623","https://openalex.org/W1990061958","https://openalex.org/W2001496424","https://openalex.org/W2020876977","https://openalex.org/W2024797550","https://openalex.org/W2038044292","https://openalex.org/W2058903936","https://openalex.org/W2061884758","https://openalex.org/W2095897464","https://openalex.org/W2106642566","https://openalex.org/W2111399468","https://openalex.org/W2112173399","https://openalex.org/W2113836856","https://openalex.org/W2118269922","https://openalex.org/W2123645388","https://openalex.org/W2128061541","https://openalex.org/W2129978134","https://openalex.org/W2131687179","https://openalex.org/W2132331529","https://openalex.org/W2136393336","https://openalex.org/W2142807163","https://openalex.org/W2143275903","https://openalex.org/W2151135734","https://openalex.org/W2153516438","https://openalex.org/W2157092487","https://openalex.org/W2161936973","https://openalex.org/W2164501930","https://openalex.org/W2610179052","https://openalex.org/W2611200784","https://openalex.org/W2911302472","https://openalex.org/W3041834803","https://openalex.org/W4251697274","https://openalex.org/W4285719527","https://openalex.org/W6624626827","https://openalex.org/W6655835823"],"related_works":["https://openalex.org/W2357844625","https://openalex.org/W2106024890","https://openalex.org/W2536894089","https://openalex.org/W215805633","https://openalex.org/W2189177577","https://openalex.org/W2401139123","https://openalex.org/W2360646659","https://openalex.org/W2590489024","https://openalex.org/W1975413421","https://openalex.org/W1914037376"],"abstract_inverted_index":{"XML":[0,24,48,65,115,142,222,261],"is":[1,25,37,63],"widely":[2],"recognized":[3],"as":[4,54],"the":[5,29,44,64,75,100,147,167,196,218,244,248,270],"data":[6,17,33,49,143,162,168,262],"interchange":[7],"standard":[8],"of":[9,12,21,46,60,114,121,127,149,161,177,203,220,231,243,251,257,266,273],"tomorrow":[10],"because":[11],"its":[13],"ability":[14],"to":[15,27,93,96,152,165,186,210,216],"represent":[16],"from":[18,34],"a":[19,137,157,174,178,201,227],"variety":[20],"sources.":[22],"Hence,":[23],"likely":[26],"be":[28,80,97,134],"format":[30],"through":[31,51],"which":[32],"multiple":[35],"sources":[36,50,144],"integrated.":[38],"In":[39],"this":[40,61,154,235],"article,":[41],"we":[42,182,238],"study":[43],"problem":[45],"integrating":[47],"correlations":[52],"realized":[53],"join":[55,101,193,223],"operations.":[56,224],"A":[57],"challenging":[58],"aspect":[59],"operation":[62],"document":[66],"structure.":[67,84],"Two":[68],"documents":[69,116],"might":[70],"convey":[71],"approximately":[72],"or":[73],"exactly":[74],"same":[76],"information":[77],"but":[78],"may":[79],"quite":[81],"different":[82],"in":[83,89,91,108,136,241],"Consequently,":[85],"an":[86,105],"approximate":[87,106,221],"match":[88,107],"structure,":[90],"addition":[92],"content,":[94],"has":[95],"folded":[98],"into":[99],"operation.":[102,155],"We":[103,123,170,189,205,225,246],"quantify":[104],"structure":[109],"and":[110,145,181,237,259,268],"content":[111],"for":[112,139,234],"pairs":[113],"using":[117,195,254],"well":[118,212],"defined":[119],"notions":[120,126],"distance.":[122],"show":[124],"how":[125],"distance":[128,199],"that":[129],"have":[130],"metric":[131],"properties":[132],"can":[133],"incorporated":[135],"framework":[138,194],"joins":[140],"between":[141,200],"introduce":[146],"idea":[148],"reference":[150,158,179],"sets":[151],"facilitate":[153],"Intuitively,":[156],"set":[159],"consists":[160],"elements":[163],"used":[164],"project":[166],"space.":[169],"characterize":[171],"what":[172],"constitutes":[173],"good":[175],"choice":[176],"set,":[180],"propose":[183],"sampling-based":[184],"algorithms":[185],"identify":[187],"them.":[188],"then":[190],"instantiate":[191,239],"our":[192,208,252,274],"tree":[197],"edit":[198],"pair":[202],"trees.":[204],"next":[206],"turn":[207],"attention":[209],"utilizing":[211],"known":[213],"index":[214,232],"structures":[215,233],"improve":[217],"performance":[219,271],"present":[226],"methodology":[228],"enabling":[229],"adaptation":[230],"problem,":[236],"it":[240],"terms":[242],"R-tree.":[245],"demonstrate":[247],"practical":[249],"utility":[250],"solutions":[253],"large":[255],"collections":[256],"real":[258],"synthetic":[260],"sets,":[263],"varying":[264],"parameters":[265],"interest,":[267],"highlighting":[269],"benefits":[272],"approach.":[275]},"counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2015,"cited_by_count":3},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":2}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}