{"id":"https://openalex.org/W1999823970","doi":"https://doi.org/10.1016/s0306-4379(01)00041-2","title":"A knowledge-based approach for duplicate elimination in data cleaning","display_name":"A knowledge-based approach for duplicate elimination in data cleaning","publication_year":2001,"publication_date":"2001-12-01","ids":{"openalex":"https://openalex.org/W1999823970","doi":"https://doi.org/10.1016/s0306-4379(01)00041-2","mag":"1999823970"},"language":"en","primary_location":{"id":"doi:10.1016/s0306-4379(01)00041-2","is_oa":false,"landing_page_url":"https://doi.org/10.1016/s0306-4379(01)00041-2","pdf_url":null,"source":{"id":"https://openalex.org/S193006928","display_name":"Information Systems","issn_l":"0306-4379","issn":["0306-4379","1873-6076"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Information Systems","raw_type":"journal-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/A5055654651","display_name":"Wai Lup Low","orcid":null},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":true,"raw_author_name":"Wai Lup Low","raw_affiliation_strings":["School of Computing, National University of Singapore, 3 Science Drive 2, 117543 Singapore"],"affiliations":[{"raw_affiliation_string":"School of Computing, National University of Singapore, 3 Science Drive 2, 117543 Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019988958","display_name":"Mong Li Lee","orcid":"https://orcid.org/0000-0002-9636-388X"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Mong Li Lee","raw_affiliation_strings":["School of Computing, National University of Singapore, 3 Science Drive 2, 117543 Singapore"],"affiliations":[{"raw_affiliation_string":"School of Computing, National University of Singapore, 3 Science Drive 2, 117543 Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5037961481","display_name":"Tok Wang Ling","orcid":"https://orcid.org/0000-0002-0496-0565"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Tok Wang Ling","raw_affiliation_strings":["School of Computing, National University of Singapore, 3 Science Drive 2, 117543 Singapore"],"affiliations":[{"raw_affiliation_string":"School of Computing, National University of Singapore, 3 Science Drive 2, 117543 Singapore","institution_ids":["https://openalex.org/I165932596"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5055654651"],"corresponding_institution_ids":["https://openalex.org/I165932596"],"apc_list":{"value":2970,"currency":"USD","value_usd":2970},"apc_paid":null,"fwci":6.0036,"has_fulltext":false,"cited_by_count":102,"citation_normalized_percentile":{"value":0.96022234,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"26","issue":"8","first_page":"585","last_page":"606"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9998999834060669,"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":0.9998999834060669,"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/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.9943000078201294,"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":0.9692999720573425,"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":0.8159594535827637},{"id":"https://openalex.org/keywords/precision-and-recall","display_name":"Precision and recall","score":0.7755287885665894},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.6082146167755127},{"id":"https://openalex.org/keywords/recall","display_name":"Recall","score":0.602288007736206},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5718756318092346},{"id":"https://openalex.org/keywords/dilemma","display_name":"Dilemma","score":0.48600420355796814},{"id":"https://openalex.org/keywords/transitive-relation","display_name":"Transitive relation","score":0.4401968717575073},{"id":"https://openalex.org/keywords/sliding-window-protocol","display_name":"Sliding window protocol","score":0.43472468852996826},{"id":"https://openalex.org/keywords/window","display_name":"Window (computing)","score":0.35704851150512695},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3209426999092102},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.23398008942604065},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07155060768127441}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8159594535827637},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.7755287885665894},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.6082146167755127},{"id":"https://openalex.org/C100660578","wikidata":"https://www.wikidata.org/wiki/Q18733","display_name":"Recall","level":2,"score":0.602288007736206},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5718756318092346},{"id":"https://openalex.org/C2778496695","wikidata":"https://www.wikidata.org/wiki/Q254128","display_name":"Dilemma","level":2,"score":0.48600420355796814},{"id":"https://openalex.org/C191399111","wikidata":"https://www.wikidata.org/wiki/Q64861","display_name":"Transitive relation","level":2,"score":0.4401968717575073},{"id":"https://openalex.org/C102392041","wikidata":"https://www.wikidata.org/wiki/Q592860","display_name":"Sliding window protocol","level":3,"score":0.43472468852996826},{"id":"https://openalex.org/C2778751112","wikidata":"https://www.wikidata.org/wiki/Q835016","display_name":"Window (computing)","level":2,"score":0.35704851150512695},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3209426999092102},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.23398008942604065},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07155060768127441},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1016/s0306-4379(01)00041-2","is_oa":false,"landing_page_url":"https://doi.org/10.1016/s0306-4379(01)00041-2","pdf_url":null,"source":{"id":"https://openalex.org/S193006928","display_name":"Information Systems","issn_l":"0306-4379","issn":["0306-4379","1873-6076"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Information Systems","raw_type":"journal-article"},{"id":"pmh:oai:scholarbank.nus.edu.sg:10635/39075","is_oa":false,"landing_page_url":"http://scholarbank.nus.edu.sg/handle/10635/39075","pdf_url":null,"source":{"id":"https://openalex.org/S7407052290","display_name":"National University of Singapore","issn_l":null,"issn":[],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Scopus","raw_type":"Article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Sustainable cities and communities","id":"https://metadata.un.org/sdg/11","score":0.47999998927116394}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W53626277","https://openalex.org/W79144062","https://openalex.org/W1490065891","https://openalex.org/W1524002271","https://openalex.org/W1568285589","https://openalex.org/W1569123402","https://openalex.org/W1596131987","https://openalex.org/W1612155886","https://openalex.org/W1638026557","https://openalex.org/W1768893245","https://openalex.org/W1898496839","https://openalex.org/W1971324061","https://openalex.org/W2006341703","https://openalex.org/W2020191321","https://openalex.org/W2024770506","https://openalex.org/W2038281398","https://openalex.org/W2070911018","https://openalex.org/W2089634871","https://openalex.org/W2116502002","https://openalex.org/W2118536331","https://openalex.org/W2130799604","https://openalex.org/W2131576956","https://openalex.org/W2137433505","https://openalex.org/W2150698190","https://openalex.org/W4285719527","https://openalex.org/W4299822035"],"related_works":["https://openalex.org/W4312527695","https://openalex.org/W2361167282","https://openalex.org/W2091342995","https://openalex.org/W1528932152","https://openalex.org/W1677394555","https://openalex.org/W3007067598","https://openalex.org/W3014558862","https://openalex.org/W2358294942","https://openalex.org/W4367460280","https://openalex.org/W4328049145"],"abstract_inverted_index":null,"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":5},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":2},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":6},{"year":2013,"cited_by_count":9},{"year":2012,"cited_by_count":6}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2016-06-24T00:00:00"}
