乐胖代购免代理版

{"id":"https://openalex.org/W2116544254","doi":"https://doi.org/10.1145/775152.775166","title":"Text joins in an RDBMS for web data integration","display_name":"Text joins in an RDBMS for web data integration","publication_year":2003,"publication_date":"2003-01-01","ids":{"openalex":"https://openalex.org/W2116544254","doi":"https://doi.org/10.1145/775152.775166","mag":"2116544254"},"language":"en","primary_location":{"is_oa":false,"landing_page_url":"https://doi.org/10.1145/775152.775166","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false},"type":"article","type_crossref":"proceedings-article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://www1.cs.columbia.edu/~gravano/Papers/2003/www03.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5080063580","display_name":"Luis Gravano","orcid":null},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Luis Gravano","raw_affiliation_strings":["Columbia University"],"affiliations":[{"raw_affiliation_string":"Columbia University","institution_ids":["https://openalex.org/I78577930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010731709","display_name":"Panagiotis G. Ipeirotis","orcid":"https://orcid.org/0000-0002-2966-7402"},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Panagiotis G. Ipeirotis","raw_affiliation_strings":["Columbia University"],"affiliations":[{"raw_affiliation_string":"Columbia University","institution_ids":["https://openalex.org/I78577930"]}]},{"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":"Nick Koudas","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/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"]}]}],"institution_assertions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":11.542,"has_fulltext":true,"fulltext_origin":"ngrams","cited_by_count":171,"citation_normalized_percentile":{"value":0.976543,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9999,"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":0.9999,"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/T10317","display_name":"Advanced Database Systems and Queries","score":0.9988,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9983,"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/cosine-similarity","display_name":"Cosine similarity","score":0.55799395}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.883566},{"id":"https://openalex.org/C2778692605","wikidata":"https://www.wikidata.org/wiki/Q4041866","display_name":"Joins","level":2,"score":0.6858019},{"id":"https://openalex.org/C24394798","wikidata":"https://www.wikidata.org/wiki/Q192588","display_name":"Relational database management system","level":3,"score":0.6703828},{"id":"https://openalex.org/C72634772","wikidata":"https://www.wikidata.org/wiki/Q386824","display_name":"Data integration","level":2,"score":0.5693488},{"id":"https://openalex.org/C510870499","wikidata":"https://www.wikidata.org/wiki/Q47607","display_name":"SQL","level":2,"score":0.56730324},{"id":"https://openalex.org/C2780762811","wikidata":"https://www.wikidata.org/wiki/Q1784941","display_name":"Cosine similarity","level":3,"score":0.55799395},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.547112},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.47153884},{"id":"https://openalex.org/C5655090","wikidata":"https://www.wikidata.org/wiki/Q192588","display_name":"Relational database","level":2,"score":0.4649922},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.45521376},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.37027767},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.19811192},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.11336437},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.10661879}],"mesh":[],"locations_count":2,"locations":[{"is_oa":false,"landing_page_url":"https://doi.org/10.1145/775152.775166","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false},{"is_oa":true,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.331.4094","pdf_url":"http://www1.cs.columbia.edu/~gravano/Papers/2003/www03.pdf","source":{"id":"https://openalex.org/S4306400349","display_name":"CiteSeer X (The Pennsylvania State University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I130769515","host_organization_name":"Pennsylvania State University","host_organization_lineage":["https://openalex.org/I130769515"],"host_organization_lineage_names":["Pennsylvania State University"],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false}],"best_oa_location":{"is_oa":true,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.331.4094","pdf_url":"http://www1.cs.columbia.edu/~gravano/Papers/2003/www03.pdf","source":{"id":"https://openalex.org/S4306400349","display_name":"CiteSeer X (The Pennsylvania State University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I130769515","host_organization_name":"Pennsylvania State University","host_organization_lineage":["https://openalex.org/I130769515"],"host_organization_lineage_names":["Pennsylvania State University"],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false},"sustainable_development_goals":[],"grants":[],"datasets":[],"versions":[],"referenced_works_count":25,"referenced_works":["https://openalex.org/W1485156179","https://openalex.org/W1492896593","https://openalex.org/W1500547548","https://openalex.org/W1559390933","https://openalex.org/W1647671624","https://openalex.org/W1956559956","https://openalex.org/W1985269159","https://openalex.org/W1991360400","https://openalex.org/W2001496424","https://openalex.org/W2003203805","https://openalex.org/W2003262311","https://openalex.org/W2006997130","https://openalex.org/W2024770506","https://openalex.org/W2038281398","https://openalex.org/W2067566391","https://openalex.org/W2073471108","https://openalex.org/W2078739211","https://openalex.org/W2088179629","https://openalex.org/W2111625757","https://openalex.org/W2152401660","https://openalex.org/W2154785834","https://openalex.org/W2161936973","https://openalex.org/W2621280964","https://openalex.org/W2913519381","https://openalex.org/W47292847"],"related_works":["https://openalex.org/W45850614","https://openalex.org/W4247095193","https://openalex.org/W411760269","https://openalex.org/W2476511644","https://openalex.org/W2098812463","https://openalex.org/W2015932315","https://openalex.org/W1982455124","https://openalex.org/W1633216903","https://openalex.org/W1575529579","https://openalex.org/W1497653608"],"abstract_inverted_index":{"The":[0],"integration":[1,61,113],"of":[2,23,46,53,64,111,125,201,204,223],"data":[3,40,60,112,213],"produced":[4],"and":[5,16,51,80,166,191,221],"collected":[6],"across":[7,37,97],"autonomous,":[8],"heterogeneous":[9],"web":[10,98,168],"services":[11],"is":[12,41,62],"an":[13,132,184,202],"increasingly":[14],"important":[15],"challenging":[17],"problem.":[18],"Due":[19],"to":[20,68,92,106,135],"the":[21,26,69,77,86,123,136,181,219],"lack":[22,52],"global":[24],"identifiers,":[25],"same":[27,70],"entity":[28],"(e.g.,":[29],"a":[30,115,128,148,156,175,197,208],"product)":[31],"might":[32],"have":[33],"different":[34],"textual":[35,120],"representations":[36],"databases.":[38],"Textual":[39],"also":[42],"often":[43],"noisy":[44],"because":[45],"transcription":[47],"errors,":[48],"incomplete":[49],"information,":[50],"standard":[54],"formats.":[55],"A":[56],"fundamental":[57],"task":[58],"during":[59],"matching":[63],"strings":[65],"that":[66],"refer":[67],"entity.":[71],"In":[72],"this":[73,103,108],"paper,":[74],"we":[75,146,195],"adopt":[76],"widely":[78],"used":[79],"established":[81],"cosine":[82],"similarity":[83,104,124],"metric":[84,105],"from":[85],"information":[87],"retrieval":[88],"field":[89],"in":[90,155],"order":[91],"identify":[93],"potential":[94],"string":[95],"matches":[96,126],"sources.":[99],"We":[100,179],"then":[101],"use":[102],"characterize":[107],"key":[109],"aspect":[110],"as":[114],"join":[116,138,150,182],"between":[117],"relations":[118],"on":[119],"attributes,":[121],"where":[122],"exceeds":[127],"specified":[129],"threshold.":[130],"Computing":[131],"exact":[133],"answer":[134],"text":[137],"can":[139],"be":[140],"expensive.":[141],"For":[142],"query":[143],"processing":[144],"efficiency,":[145],"propose":[147],"sampling-based":[149],"approximation":[151],"strategy":[152],"for":[153,189],"execution":[154],"standard,":[157],"unmodified":[158],"relational":[159],"database":[160],"management":[161],"system":[162],"(RDBMS),":[163],"since":[164],"more":[165,167],"sites":[169],"are":[170],"powered":[171],"by":[172],"RDBMSs":[173],"with":[174],"web-based":[176],"front":[177],"end.":[178],"implement":[180],"inside":[183],"RDBMS,":[185,210],"using":[186,211],"SQL":[187],"queries,":[188],"scalability":[190],"robustness":[192],"reasons.":[193],"Finally,":[194],"present":[196],"detailed":[198],"performance":[199],"evaluation":[200],"implementation":[203],"our":[205,224],"algorithm":[206],"within":[207],"commercial":[209],"real-life":[212],"sets.":[214],"Our":[215],"experimental":[216],"results":[217],"demonstrate":[218],"efficiency":[220],"accuracy":[222],"techniques.":[225]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W2116544254","counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":8},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":6},{"year":2014,"cited_by_count":14},{"year":2013,"cited_by_count":7},{"year":2012,"cited_by_count":8}],"updated_date":"2024-12-08T01:35:18.394775","created_date":"2016-06-24"}