{"id":"https://openalex.org/W2132331529","doi":"https://doi.org/10.1109/icde.2003.1260843","title":"Index-based approximate XML joins","display_name":"Index-based approximate XML joins","publication_year":2004,"publication_date":"2004-05-06","ids":{"openalex":"https://openalex.org/W2132331529","doi":"https://doi.org/10.1109/icde.2003.1260843","mag":"2132331529"},"language":"en","primary_location":{"id":"doi:10.1109/icde.2003.1260843","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icde.2003.1260843","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings 19th International Conference on Data Engineering (Cat. No.03CH37405)","raw_type":"proceedings-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/A5017534381","display_name":"Suvajyoti Guha","orcid":"https://orcid.org/0000-0002-7622-2721"},"institutions":[{"id":"https://openalex.org/I79576946","display_name":"University of Pennsylvania","ror":"https://ror.org/00b30xv10","country_code":"US","type":"education","lineage":["https://openalex.org/I79576946"]},{"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":"S. Guha","raw_affiliation_strings":["University of Pennsylvania, USA","[Pennsylvania Univ., Philadelphia, PA, USA]"],"affiliations":[{"raw_affiliation_string":"University of Pennsylvania, USA","institution_ids":["https://openalex.org/I36788626"]},{"raw_affiliation_string":"[Pennsylvania Univ., Philadelphia, PA, USA]","institution_ids":["https://openalex.org/I79576946"]}]},{"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/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":"N. Koudas","raw_affiliation_strings":["AT and T Research Laboratories, USA","At&T#TAB#"],"affiliations":[{"raw_affiliation_string":"AT and T Research Laboratories, USA","institution_ids":["https://openalex.org/I1283103587"]},{"raw_affiliation_string":"At&T#TAB#","institution_ids":["https://openalex.org/I1283103587"]}]},{"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 and T Research Laboratories, USA","At&T#TAB#"],"affiliations":[{"raw_affiliation_string":"AT and T Research Laboratories, USA","institution_ids":["https://openalex.org/I1283103587"]},{"raw_affiliation_string":"At&T#TAB#","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/I2801919071","display_name":"University of Illinois System","ror":"https://ror.org/05e94g991","country_code":"US","type":"education","lineage":["https://openalex.org/I2801919071"]},{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"T. Yu","raw_affiliation_strings":["University of Illinois, USA","University of Illinois at Urbana Champaign"],"affiliations":[{"raw_affiliation_string":"University of Illinois, USA","institution_ids":["https://openalex.org/I2801919071"]},{"raw_affiliation_string":"University of Illinois at Urbana Champaign","institution_ids":["https://openalex.org/I157725225"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5017534381"],"corresponding_institution_ids":["https://openalex.org/I36788626","https://openalex.org/I79576946"],"apc_list":null,"apc_paid":null,"fwci":2.2855,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.88750783,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"708","last_page":"710"},"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":0.9995999932289124,"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/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9955000281333923,"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":0.8500905632972717},{"id":"https://openalex.org/keywords/joins","display_name":"Joins","score":0.756141185760498},{"id":"https://openalex.org/keywords/xml","display_name":"XML","score":0.7518854141235352},{"id":"https://openalex.org/keywords/document-structure-description","display_name":"Document Structure Description","score":0.6358332633972168},{"id":"https://openalex.org/keywords/efficient-xml-interchange","display_name":"Efficient XML Interchange","score":0.5859944820404053},{"id":"https://openalex.org/keywords/xml-validation","display_name":"XML validation","score":0.5623217821121216},{"id":"https://openalex.org/keywords/index","display_name":"Index (typography)","score":0.5101602673530579},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.5012876987457275},{"id":"https://openalex.org/keywords/xml-database","display_name":"XML database","score":0.4946140944957733},{"id":"https://openalex.org/keywords/xml-schema","display_name":"XML Schema (W3C)","score":0.47353336215019226},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.47016260027885437},{"id":"https://openalex.org/keywords/xml-schema-editor","display_name":"XML Schema Editor","score":0.4612841010093689},{"id":"https://openalex.org/keywords/streaming-xml","display_name":"Streaming XML","score":0.44248050451278687},{"id":"https://openalex.org/keywords/join","display_name":"Join (topology)","score":0.44017383456230164},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.43611446022987366},{"id":"https://openalex.org/keywords/tree","display_name":"Tree (set theory)","score":0.4278873801231384},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.3618200421333313},{"id":"https://openalex.org/keywords/document-type-definition","display_name":"Document type definition","score":0.3000999987125397},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.16314327716827393},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.16072434186935425},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.09028962254524231},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.06856000423431396}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8500905632972717},{"id":"https://openalex.org/C2778692605","wikidata":"https://www.wikidata.org/wiki/Q4041866","display_name":"Joins","level":2,"score":0.756141185760498},{"id":"https://openalex.org/C8797682","wikidata":"https://www.wikidata.org/wiki/Q2115","display_name":"XML","level":2,"score":0.7518854141235352},{"id":"https://openalex.org/C68699486","wikidata":"https://www.wikidata.org/wiki/Q265904","display_name":"Document Structure Description","level":3,"score":0.6358332633972168},{"id":"https://openalex.org/C11508877","wikidata":"https://www.wikidata.org/wiki/Q1124477","display_name":"Efficient XML Interchange","level":3,"score":0.5859944820404053},{"id":"https://openalex.org/C55348073","wikidata":"https://www.wikidata.org/wiki/Q595926","display_name":"XML validation","level":3,"score":0.5623217821121216},{"id":"https://openalex.org/C2777382242","wikidata":"https://www.wikidata.org/wiki/Q6017816","display_name":"Index (typography)","level":2,"score":0.5101602673530579},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.5012876987457275},{"id":"https://openalex.org/C183068750","wikidata":"https://www.wikidata.org/wiki/Q357393","display_name":"XML database","level":3,"score":0.4946140944957733},{"id":"https://openalex.org/C40713593","wikidata":"https://www.wikidata.org/wiki/Q16342","display_name":"XML Schema (W3C)","level":5,"score":0.47353336215019226},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.47016260027885437},{"id":"https://openalex.org/C34716815","wikidata":"https://www.wikidata.org/wiki/Q8042322","display_name":"XML Schema Editor","level":3,"score":0.4612841010093689},{"id":"https://openalex.org/C44883583","wikidata":"https://www.wikidata.org/wiki/Q7622687","display_name":"Streaming XML","level":3,"score":0.44248050451278687},{"id":"https://openalex.org/C2776124973","wikidata":"https://www.wikidata.org/wiki/Q3183033","display_name":"Join (topology)","level":2,"score":0.44017383456230164},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.43611446022987366},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.4278873801231384},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.3618200421333313},{"id":"https://openalex.org/C84314905","wikidata":"https://www.wikidata.org/wiki/Q212327","display_name":"Document type definition","level":4,"score":0.3000999987125397},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.16314327716827393},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.16072434186935425},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.09028962254524231},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.06856000423431396},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icde.2003.1260843","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icde.2003.1260843","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings 19th International Conference on Data Engineering (Cat. No.03CH37405)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.65.6730","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.65.6730","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.research.att.com/~divesh/papers/gksy2003-approxindexjoin.poster.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":7,"referenced_works":["https://openalex.org/W93804029","https://openalex.org/W1533573623","https://openalex.org/W2118269922","https://openalex.org/W2132331529","https://openalex.org/W2161936973","https://openalex.org/W2164501930","https://openalex.org/W6631796798"],"related_works":["https://openalex.org/W2378161351","https://openalex.org/W56234146","https://openalex.org/W2401139123","https://openalex.org/W2536894089","https://openalex.org/W2103912919","https://openalex.org/W2076199141","https://openalex.org/W2787219442","https://openalex.org/W144877966","https://openalex.org/W1914037376","https://openalex.org/W2590489024"],"abstract_inverted_index":{"XML":[0,40,59,101],"data":[1,32,41],"integration":[2],"tools":[3],"are":[4],"facing":[5],"a":[6,23,68],"variety":[7,24],"of":[8,25,38,50,58,86],"challenges":[9],"for":[10,96,110,117],"their":[11],"efficient":[12],"and":[13,56,71,93],"effective":[14],"operation.":[15],"Among":[16],"these":[17],"is":[18],"the":[19,31,36,54,62,77,84],"requirement":[20],"to":[21,82,99],"handle":[22],"inconsistencies":[26],"or":[27],"mistakes":[28],"present":[29],"in":[30,53],"sets.":[33],"We":[34,65,89,104],"study":[35],"problem":[37],"integrating":[39],"sources":[42],"through":[43],"index":[44,74,100],"assisted":[45],"join":[46,63,94],"operations,":[47],"using":[48],"notions":[49],"approximate":[51],"match":[52],"structure":[55],"content":[57],"documents":[60],"as":[61],"predicate.":[64],"show":[66],"how":[67],"well":[69],"known":[70],"widely":[72],"deployed":[73],"structure,":[75],"namely":[76],"R-tree,":[78],"can":[79],"be":[80],"adopted":[81,98],"improve":[83],"performance":[85],"such":[87],"operations.":[88],"propose":[90,106],"novel":[91,107],"search":[92],"algorithms":[95],"R-trees":[97,114],"document":[102],"collections.":[103],"also":[105],"optimization":[108],"objectives":[109],"R-tree":[111],"construction,":[112],"making":[113],"better":[115],"suited":[116],"this":[118],"application.":[119]},"counts_by_year":[],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}