{"id":"https://openalex.org/W2102239864","doi":"https://doi.org/10.1145/1871437.1871627","title":"PruSM","display_name":"PruSM","publication_year":2010,"publication_date":"2010-10-26","ids":{"openalex":"https://openalex.org/W2102239864","doi":"https://doi.org/10.1145/1871437.1871627","mag":"2102239864"},"language":"en","primary_location":{"id":"doi:10.1145/1871437.1871627","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1871437.1871627","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 19th ACM international conference on Information and knowledge management","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/A5113594356","display_name":"Thanh Hoang Nguyen","orcid":null},"institutions":[{"id":"https://openalex.org/I223532165","display_name":"University of Utah","ror":"https://ror.org/03r0ha626","country_code":"US","type":"education","lineage":["https://openalex.org/I223532165"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Thanh Hoang Nguyen","raw_affiliation_strings":["Unversity of Utah, Salt Lake City, UT, USA"],"affiliations":[{"raw_affiliation_string":"Unversity of Utah, Salt Lake City, UT, USA","institution_ids":["https://openalex.org/I223532165"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101764273","display_name":"Hoa T. Nguyen","orcid":"https://orcid.org/0000-0001-6904-6312"},"institutions":[{"id":"https://openalex.org/I223532165","display_name":"University of Utah","ror":"https://ror.org/03r0ha626","country_code":"US","type":"education","lineage":["https://openalex.org/I223532165"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hoa Nguyen","raw_affiliation_strings":["Unversity of Utah, Salt Lake City, UT, USA"],"affiliations":[{"raw_affiliation_string":"Unversity of Utah, Salt Lake City, UT, USA","institution_ids":["https://openalex.org/I223532165"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5006773757","display_name":"Juliana Freire","orcid":"https://orcid.org/0000-0003-3915-7075"},"institutions":[{"id":"https://openalex.org/I223532165","display_name":"University of Utah","ror":"https://ror.org/03r0ha626","country_code":"US","type":"education","lineage":["https://openalex.org/I223532165"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Juliana Freire","raw_affiliation_strings":["Unversity of Utah, Salt Lake City, UT, USA"],"affiliations":[{"raw_affiliation_string":"Unversity of Utah, Salt Lake City, UT, USA","institution_ids":["https://openalex.org/I223532165"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5113594356"],"corresponding_institution_ids":["https://openalex.org/I223532165"],"apc_list":null,"apc_paid":null,"fwci":6.2433,"has_fulltext":false,"cited_by_count":20,"citation_normalized_percentile":{"value":0.96431026,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1385","last_page":"1388"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":1.0,"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/T12016","display_name":"Web Data Mining and Analysis","score":1.0,"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/T10317","display_name":"Advanced Database Systems and Queries","score":0.9965999722480774,"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/T11719","display_name":"Data Quality and Management","score":0.996399998664856,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8672583699226379},{"id":"https://openalex.org/keywords/schema-matching","display_name":"Schema matching","score":0.748879611492157},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.5268422961235046},{"id":"https://openalex.org/keywords/schema","display_name":"Schema (genetic algorithms)","score":0.5137389898300171},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.5135557651519775},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.46237537264823914},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.456729918718338},{"id":"https://openalex.org/keywords/data-integration","display_name":"Data integration","score":0.3707505464553833},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.1967710554599762}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8672583699226379},{"id":"https://openalex.org/C2777327318","wikidata":"https://www.wikidata.org/wiki/Q1408390","display_name":"Schema matching","level":3,"score":0.748879611492157},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.5268422961235046},{"id":"https://openalex.org/C52146309","wikidata":"https://www.wikidata.org/wiki/Q7431116","display_name":"Schema (genetic algorithms)","level":2,"score":0.5137389898300171},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5135557651519775},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.46237537264823914},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.456729918718338},{"id":"https://openalex.org/C72634772","wikidata":"https://www.wikidata.org/wiki/Q386824","display_name":"Data integration","level":2,"score":0.3707505464553833},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.1967710554599762},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1871437.1871627","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1871437.1871627","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 19th ACM international conference on Information and knowledge management","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","score":0.5099999904632568,"display_name":"Industry, innovation and infrastructure"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W291262356","https://openalex.org/W343945789","https://openalex.org/W1534024124","https://openalex.org/W1545169732","https://openalex.org/W1660390307","https://openalex.org/W2008896880","https://openalex.org/W2016892599","https://openalex.org/W2064693822","https://openalex.org/W2110034127","https://openalex.org/W2116595366","https://openalex.org/W2117058208","https://openalex.org/W2118356300","https://openalex.org/W2118966476","https://openalex.org/W2130578025","https://openalex.org/W2148738951","https://openalex.org/W2150365753","https://openalex.org/W2156510574","https://openalex.org/W2160683489","https://openalex.org/W2171262729","https://openalex.org/W2171516661","https://openalex.org/W3004612262","https://openalex.org/W6637101025","https://openalex.org/W6682897514"],"related_works":["https://openalex.org/W1528218860","https://openalex.org/W2406112091","https://openalex.org/W2125859764","https://openalex.org/W1128683088","https://openalex.org/W2372910313","https://openalex.org/W3138074544","https://openalex.org/W4310041472","https://openalex.org/W2938811602","https://openalex.org/W2036644834","https://openalex.org/W2408969024"],"abstract_inverted_index":{"There":[0],"has":[1,97],"been":[2,98],"a":[3,81,129,159,171,201],"substantial":[4],"increase":[5],"in":[6,84,100,170],"the":[7,39,62,101,148,164,175,193],"number":[8,131,203],"of":[9,132,177,184,204],"Web":[10,51],"data":[11,43,143,189],"sources":[12],"whose":[13],"contents":[14],"are":[15,120],"hidden":[16],"and":[17,37,48,115,122,150,196,207],"can":[18,71],"only":[19,110],"be":[20],"accessed":[21],"through":[22,125],"form":[23,85,113,118,138,168,205],"interfaces.":[24],"To":[25],"leverage":[26],"this":[27,77,95],"data,":[28],"several":[29],"applications":[30,60],"have":[31,105],"emerged":[32],"that":[33,69,117,192],"aim":[34],"to":[35,41,50,64,88,198],"automate":[36],"simplify":[38],"access":[40],"these":[42,59,66],"sources,":[44],"from":[45],"hidden-Web":[46],"crawlers":[47],"meta-searchers":[49],"information":[52],"integration":[53],"systems.":[54],"A":[55,181],"requirement":[56],"shared":[57],"by":[58,153],"is":[61,134,145],"ability":[63],"understand":[65],"forms,":[67],"so":[68],"they":[70,109],"automatically":[72,135],"fill":[73],"them":[74],"out.":[75],"In":[76],"paper,":[78],"we":[79],"address":[80],"key":[82],"problem":[83,96],"understanding:":[86],"how":[87],"match":[89,200],"elements":[90,119,169],"across":[91],"distinct":[92],"forms.":[93],"Although":[94],"studied":[99],"literature,":[102],"existing":[103],"approaches":[104],"important":[106],"limitations.":[107],"Notably,":[108],"handle":[111],"small":[112],"collections":[114],"assume":[116],"clean":[121],"normalized,":[123],"often":[124],"manual":[126,211],"pre-processing.":[127,212],"When":[128],"large":[130,202],"forms":[133],"gathered,":[136],"matching":[137,162],"schemata":[139,206],"presents":[140],"new":[141],"challenges:":[142],"heterogeneity":[144],"compounded":[146],"with":[147,174],"Web-scale":[149],"noise":[151],"introduced":[152],"automated":[154],"processes.":[155],"We":[156],"propose":[157],"PruSM,":[158],"prudent":[160,172],"schema":[161],"strategy":[163],"determines":[165],"matches":[166],"for":[167],"fashion,":[173],"goal":[176],"minimizing":[178],"error":[179],"propagation.":[180],"experimental":[182],"evaluation":[183],"PruSM":[185],"using":[186],"widely":[187],"available":[188],"sets":[190],"shows":[191],"approach":[194],"effective":[195],"able":[197],"accurately":[199],"without":[208],"requiring":[209],"any":[210]},"counts_by_year":[{"year":2017,"cited_by_count":4},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":4},{"year":2012,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2016-06-24T00:00:00"}