{"id":"https://openalex.org/W2086937365","doi":"https://doi.org/10.1145/2396761.2398406","title":"An effective rule miner for instance matching in a web of data","display_name":"An effective rule miner for instance matching in a web of data","publication_year":2012,"publication_date":"2012-10-29","ids":{"openalex":"https://openalex.org/W2086937365","doi":"https://doi.org/10.1145/2396761.2398406","mag":"2086937365"},"language":"en","primary_location":{"id":"doi:10.1145/2396761.2398406","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2396761.2398406","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 21st 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/A5103143790","display_name":"Xing Niu","orcid":"https://orcid.org/0000-0003-3006-9546"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xing Niu","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China","[Shanghai Jiao Tong University, Shanghai, China]"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"[Shanghai Jiao Tong University, Shanghai, China]","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066421366","display_name":"Rong Shu","orcid":"https://orcid.org/0000-0002-3620-4617"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shu Rong","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China","[Shanghai Jiao Tong University, Shanghai, China]"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"[Shanghai Jiao Tong University, Shanghai, China]","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039059501","display_name":"Haofen Wang","orcid":"https://orcid.org/0000-0003-3018-3824"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haofen Wang","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China","[Shanghai Jiao Tong University, Shanghai, China]"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"[Shanghai Jiao Tong University, Shanghai, China]","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001571390","display_name":"Yong Yu","orcid":"https://orcid.org/0000-0003-0281-8271"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yong Yu","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China","[Shanghai Jiao Tong University, Shanghai, China]"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"[Shanghai Jiao Tong University, Shanghai, China]","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5103143790"],"corresponding_institution_ids":["https://openalex.org/I183067930"],"apc_list":null,"apc_paid":null,"fwci":1.9994,"has_fulltext":false,"cited_by_count":39,"citation_normalized_percentile":{"value":0.87446957,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1085","last_page":"1094"},"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/T10215","display_name":"Semantic Web and Ontologies","score":0.9990000128746033,"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"}},{"id":"https://openalex.org/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9959999918937683,"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":0.845404863357544},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.6495718955993652},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.6354407072067261},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.6199014782905579},{"id":"https://openalex.org/keywords/rewriting","display_name":"Rewriting","score":0.5570968985557556},{"id":"https://openalex.org/keywords/sparql","display_name":"SPARQL","score":0.5434823036193848},{"id":"https://openalex.org/keywords/heuristic","display_name":"Heuristic","score":0.5334610939025879},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5229107737541199},{"id":"https://openalex.org/keywords/linked-data","display_name":"Linked data","score":0.4438285231590271},{"id":"https://openalex.org/keywords/data-integration","display_name":"Data integration","score":0.4231034517288208},{"id":"https://openalex.org/keywords/data-quality","display_name":"Data quality","score":0.4218016266822815},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.31132933497428894},{"id":"https://openalex.org/keywords/semantic-web","display_name":"Semantic Web","score":0.2890482544898987},{"id":"https://openalex.org/keywords/rdf","display_name":"RDF","score":0.2701457738876343},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2185082733631134},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.1857614815235138}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.845404863357544},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.6495718955993652},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.6354407072067261},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.6199014782905579},{"id":"https://openalex.org/C154690210","wikidata":"https://www.wikidata.org/wiki/Q1668499","display_name":"Rewriting","level":2,"score":0.5570968985557556},{"id":"https://openalex.org/C41009113","wikidata":"https://www.wikidata.org/wiki/Q54871","display_name":"SPARQL","level":4,"score":0.5434823036193848},{"id":"https://openalex.org/C173801870","wikidata":"https://www.wikidata.org/wiki/Q201413","display_name":"Heuristic","level":2,"score":0.5334610939025879},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5229107737541199},{"id":"https://openalex.org/C69075417","wikidata":"https://www.wikidata.org/wiki/Q515701","display_name":"Linked data","level":3,"score":0.4438285231590271},{"id":"https://openalex.org/C72634772","wikidata":"https://www.wikidata.org/wiki/Q386824","display_name":"Data integration","level":2,"score":0.4231034517288208},{"id":"https://openalex.org/C24756922","wikidata":"https://www.wikidata.org/wiki/Q1757694","display_name":"Data quality","level":3,"score":0.4218016266822815},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.31132933497428894},{"id":"https://openalex.org/C2129575","wikidata":"https://www.wikidata.org/wiki/Q54837","display_name":"Semantic Web","level":2,"score":0.2890482544898987},{"id":"https://openalex.org/C147497476","wikidata":"https://www.wikidata.org/wiki/Q54872","display_name":"RDF","level":3,"score":0.2701457738876343},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2185082733631134},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.1857614815235138},{"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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2396761.2398406","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2396761.2398406","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 21st ACM international conference on Information and knowledge management","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4099999964237213,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W68568358","https://openalex.org/W192652968","https://openalex.org/W1481392940","https://openalex.org/W1483669204","https://openalex.org/W1491268609","https://openalex.org/W1493691328","https://openalex.org/W1506285740","https://openalex.org/W1514849215","https://openalex.org/W1526669747","https://openalex.org/W1531486567","https://openalex.org/W1758759808","https://openalex.org/W1787541010","https://openalex.org/W1805140197","https://openalex.org/W1993783004","https://openalex.org/W1995099886","https://openalex.org/W2015191210","https://openalex.org/W2047029075","https://openalex.org/W2064853889","https://openalex.org/W2108991785","https://openalex.org/W2110848713","https://openalex.org/W2114538147","https://openalex.org/W2153225416","https://openalex.org/W2157896838","https://openalex.org/W2173213060","https://openalex.org/W2286326061","https://openalex.org/W2296113587","https://openalex.org/W2397994241","https://openalex.org/W2403886113","https://openalex.org/W2405356156","https://openalex.org/W2611894836","https://openalex.org/W2616380054","https://openalex.org/W2797148637","https://openalex.org/W4252403066","https://openalex.org/W4301347335","https://openalex.org/W6602792240","https://openalex.org/W6676486366","https://openalex.org/W6696834760","https://openalex.org/W6713488215","https://openalex.org/W6737354466","https://openalex.org/W7034062031"],"related_works":["https://openalex.org/W4206764195","https://openalex.org/W2155929612","https://openalex.org/W199330785","https://openalex.org/W2267627180","https://openalex.org/W2402575682","https://openalex.org/W2396236980","https://openalex.org/W2187569332","https://openalex.org/W98016204","https://openalex.org/W602498611","https://openalex.org/W2085965157"],"abstract_inverted_index":{"Publishing":[0],"structured":[1],"data":[2,24,77,175],"and":[3,140,195,213],"linking":[4],"them":[5,104],"to":[6,15,55,94,102,105,135,216],"Linking":[7],"Open":[8],"Data":[9],"(LOD)":[10],"is":[11],"an":[12],"ongoing":[13],"effort":[14],"create":[16],"a":[17,115,118,131],"Web":[18],"of":[19,38,121,144,158,184,189,192,198],"data.":[20],"Each":[21],"newly":[22],"involved":[23],"source":[25,78],"may":[26],"contain":[27],"duplicated":[28],"instances":[29],"(entities)":[30],"whose":[31],"descriptions":[32],"or":[33,90,108],"schemata":[34],"differ":[35],"from":[36,70],"those":[37],"the":[39,81,84,96,154,179,182,190,196],"existing":[40],"sources":[41,107,176],"in":[42,177,187],"LOD.":[43],"To":[44],"tackle":[45],"this":[46,111],"heterogeneity":[47],"issue,":[48],"several":[49,205],"matching":[50,62,73,125,138,165],"methods":[51,63],"have":[52],"been":[53],"developed":[54],"link":[56],"equivalent":[57],"entities":[58],"together.":[59],"Many":[60],"general-purpose":[61],"which":[64,98],"focus":[65],"on":[66,148,156,171],"similarity":[67,208],"metrics":[68],"suffer":[69],"very":[71],"diverse":[72],"results":[74,180],"for":[75],"different":[76,221],"pairs.":[79],"On":[80],"other":[82,106],"hand,":[83],"dataset-specific":[85,124],"ones":[86],"leverage":[87],"heuristic":[88],"rules":[89,139,160],"even":[91],"manual":[92],"efforts":[93],"ensure":[95],"quality,":[97],"makes":[99],"it":[100],"impossible":[101],"apply":[103],"domains.":[109],"In":[110,127],"paper,":[112],"we":[113,129,203],"offer":[114],"third":[116],"choice,":[117],"general":[119],"method":[120],"automatically":[122],"discovering":[123],"rules.":[126,150],"particular,":[128],"propose":[130],"semi-supervised":[132],"learning":[133],"algorithm":[134],"iteratively":[136],"refine":[137],"find":[141],"new":[142],"matches":[143,194,200],"high":[145],"confidence":[146],"based":[147],"these":[149],"This":[151],"dramatically":[152],"relieves":[153],"burden":[155],"users":[157],"defining":[159],"but":[161],"still":[162],"gives":[163],"high-quality":[164],"results.":[166],"We":[167],"carry":[168],"out":[169],"experiments":[170],"real-world":[172],"large":[173],"scale":[174],"LOD;":[178],"show":[181],"effectiveness":[183],"our":[185],"approach":[186],"terms":[188],"precision":[191],"discovered":[193],"number":[197],"missing":[199],"found.":[201],"Furthermore,":[202],"discuss":[204],"extensions":[206],"(like":[207],"embedded":[209],"rules,":[210],"class":[211],"restriction":[212],"SPARQL":[214],"rewriting)":[215],"fit":[217],"various":[218],"applications":[219],"with":[220],"requirements.":[222]},"counts_by_year":[{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":8},{"year":2020,"cited_by_count":7},{"year":2019,"cited_by_count":6},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}