{"id":"https://openalex.org/W2132658991","doi":"https://doi.org/10.1145/2433396.2433439","title":"TYPiMatch","display_name":"TYPiMatch","publication_year":2013,"publication_date":"2013-02-04","ids":{"openalex":"https://openalex.org/W2132658991","doi":"https://doi.org/10.1145/2433396.2433439","mag":"2132658991"},"language":"en","primary_location":{"id":"doi:10.1145/2433396.2433439","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2433396.2433439","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the sixth ACM international conference on Web search and data mining","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/A5101375118","display_name":"Yongtao Ma","orcid":null},"institutions":[{"id":"https://openalex.org/I102335020","display_name":"Karlsruhe Institute of Technology","ror":"https://ror.org/04t3en479","country_code":"DE","type":"education","lineage":["https://openalex.org/I102335020","https://openalex.org/I1305996414"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Yongtao Ma","raw_affiliation_strings":["AIFB of KIT, Karlsruhe, Germany","AIFB of KIT, Karlsruhe, Germany#TAB#"],"affiliations":[{"raw_affiliation_string":"AIFB of KIT, Karlsruhe, Germany","institution_ids":["https://openalex.org/I102335020"]},{"raw_affiliation_string":"AIFB of KIT, Karlsruhe, Germany#TAB#","institution_ids":["https://openalex.org/I102335020"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5105208592","display_name":"Thanh Tran","orcid":"https://orcid.org/0000-0001-8663-1652"},"institutions":[{"id":"https://openalex.org/I102335020","display_name":"Karlsruhe Institute of Technology","ror":"https://ror.org/04t3en479","country_code":"DE","type":"education","lineage":["https://openalex.org/I102335020","https://openalex.org/I1305996414"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Thanh Tran","raw_affiliation_strings":["AIFB of KIT, Karlsruhe, Germany","AIFB of KIT, Karlsruhe, Germany#TAB#"],"affiliations":[{"raw_affiliation_string":"AIFB of KIT, Karlsruhe, Germany","institution_ids":["https://openalex.org/I102335020"]},{"raw_affiliation_string":"AIFB of KIT, Karlsruhe, Germany#TAB#","institution_ids":["https://openalex.org/I102335020"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5101375118"],"corresponding_institution_ids":["https://openalex.org/I102335020"],"apc_list":null,"apc_paid":null,"fwci":4.9316,"has_fulltext":false,"cited_by_count":31,"citation_normalized_percentile":{"value":0.95220565,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"325","last_page":"334"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":1.0,"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":1.0,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9948999881744385,"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/T11106","display_name":"Data Management and Algorithms","score":0.9797999858856201,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/blocking","display_name":"Blocking (statistics)","score":0.8413597345352173},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7875178456306458},{"id":"https://openalex.org/keywords/unsupervised-learning","display_name":"Unsupervised learning","score":0.6457608938217163},{"id":"https://openalex.org/keywords/preprocessor","display_name":"Preprocessor","score":0.6384639739990234},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.6310573220252991},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.561294674873352},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5540795922279358},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.5325891971588135},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.482725590467453},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4048768877983093},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1046091616153717}],"concepts":[{"id":"https://openalex.org/C144745244","wikidata":"https://www.wikidata.org/wiki/Q4927286","display_name":"Blocking (statistics)","level":2,"score":0.8413597345352173},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7875178456306458},{"id":"https://openalex.org/C8038995","wikidata":"https://www.wikidata.org/wiki/Q1152135","display_name":"Unsupervised learning","level":2,"score":0.6457608938217163},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.6384639739990234},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.6310573220252991},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.561294674873352},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5540795922279358},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.5325891971588135},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.482725590467453},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4048768877983093},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1046091616153717},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"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:10.1145/2433396.2433439","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2433396.2433439","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the sixth ACM international conference on Web search and data mining","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W1540269031","https://openalex.org/W1597082186","https://openalex.org/W1761401273","https://openalex.org/W1981590391","https://openalex.org/W1992930793","https://openalex.org/W2015191210","https://openalex.org/W2038281398","https://openalex.org/W2046112356","https://openalex.org/W2058469523","https://openalex.org/W2073471108","https://openalex.org/W2096598900","https://openalex.org/W2107799451","https://openalex.org/W2111116800","https://openalex.org/W2111625757","https://openalex.org/W2114764731","https://openalex.org/W2117974736","https://openalex.org/W2121516976","https://openalex.org/W2127675794","https://openalex.org/W2143124645","https://openalex.org/W2164456230","https://openalex.org/W2170902582","https://openalex.org/W2171472464","https://openalex.org/W2407521136","https://openalex.org/W6632038546","https://openalex.org/W6665389842","https://openalex.org/W6674576723"],"related_works":["https://openalex.org/W17155033","https://openalex.org/W3207760230","https://openalex.org/W1496222301","https://openalex.org/W1590307681","https://openalex.org/W2536018345","https://openalex.org/W4312814274","https://openalex.org/W4285370786","https://openalex.org/W2296488620","https://openalex.org/W2358353312","https://openalex.org/W206706326"],"abstract_inverted_index":{"Instance":[0],"matching":[1,160],"and":[2,40,52,107,112,119,152,158],"blocking,":[3],"a":[4],"preprocessing":[5],"step":[6],"used":[7],"for":[8,33,57,74,103,126],"selecting":[9],"candidate":[10],"matches,":[11],"require":[12],"determining":[13],"the":[14,34,76,96,108,144],"most":[15],"representative":[16],"attributes":[17],"of":[18,36,62,147],"instances":[19,27,63,73],"called":[20],"keys,":[21],"based":[22],"on":[23,68],"which":[24,75],"similarities":[25],"between":[26],"are":[28,91,124],"computed.":[29],"We":[30,98],"show":[31,142],"that":[32,46,90,123,143],"problem":[35],"learning":[37,54,104,121,148],"blocking":[38,110,150,157],"keys":[39,111,151],"key":[41,113,153],"values,":[42],"both":[43,156],"generic":[44],"techniques":[45,55],"do":[47,64],"not":[48,65,92],"exploit":[49],"type":[50,61,78],"information":[51],"supervised":[53,118],"optimized":[56,125],"one":[58,127],"single":[59,128],"predefined":[60,77],"perform":[66],"well":[67,135],"heterogeneous":[69],"Web":[70],"data":[71],"capturing":[72],"is":[79],"too":[80],"general.":[81],"That":[82],"is,":[83],"they":[84],"actually":[85],"belong":[86],"to":[87,116],"some":[88],"subtypes":[89,106],"explicitly":[93],"specified":[94],"in":[95],"data.":[97],"propose":[99],"an":[100],"unsupervised":[101,120],"approach":[102,131],"these":[105],"subtype-specific":[109,149],"values.":[114],"Compared":[115],"state-of-the-art":[117],"approaches":[122],"type,":[129],"our":[130],"improves":[132,155],"efficiency":[133],"as":[134,136],"result":[137],"quality.":[138],"In":[139],"particular,":[140],"we":[141],"proposed":[145],"strategy":[146],"values":[154],"instance":[159],"results.":[161]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":6},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":8},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":1}],"updated_date":"2025-11-23T23:15:26.331081","created_date":"2016-06-24T00:00:00"}
