{"id":"https://openalex.org/W1966389434","doi":"https://doi.org/10.1007/s007990100044","title":"An n-gram-based approach for detecting approximately duplicate database records","display_name":"An n-gram-based approach for detecting approximately duplicate database records","publication_year":2002,"publication_date":"2002-05-01","ids":{"openalex":"https://openalex.org/W1966389434","doi":"https://doi.org/10.1007/s007990100044","mag":"1966389434"},"language":"en","primary_location":{"id":"doi:10.1007/s007990100044","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s007990100044","pdf_url":null,"source":{"id":"https://openalex.org/S110615584","display_name":"International Journal on Digital Libraries","issn_l":"1432-1300","issn":["1432-1300","1432-5012"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal on Digital Libraries","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/A5052438719","display_name":"Zengping Tian","orcid":null},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]},{"id":"https://openalex.org/I4210126794","display_name":"IBM Research (China)","ror":"https://ror.org/02yg1pf55","country_code":"CN","type":"company","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115","https://openalex.org/I4210126794"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zengping Tian","raw_affiliation_strings":["Department of Computer Science, Fudan University, Shanghi, 200433, P.R. China;","IBM China Research Laboratory, Beijing, P.R. China;","Department of Computer Science, Fudan University, Shanghi, 200433, P.R. China; E-mail: {zptian, wyji, ayzhou}@fudan.edu.cn, CN"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Fudan University, Shanghi, 200433, P.R. China;","institution_ids":["https://openalex.org/I24943067"]},{"raw_affiliation_string":"IBM China Research Laboratory, Beijing, P.R. China;","institution_ids":["https://openalex.org/I4210126794"]},{"raw_affiliation_string":"Department of Computer Science, Fudan University, Shanghi, 200433, P.R. China; E-mail: {zptian, wyji, ayzhou}@fudan.edu.cn, CN","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103551313","display_name":"Hongjun L\u00fc","orcid":null},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]},{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Hongjun Lu","raw_affiliation_strings":["Department of Computer Science, Hong Kong University of Science and Technology, Hong Kong, P.R. China;","Department of Computer Science, Hong Kong University of Science and Technology, Hong Kong, P.R. China; E-mail: luhj@cs.ust.hk, , CN"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Hong Kong University of Science and Technology, Hong Kong, P.R. China;","institution_ids":["https://openalex.org/I200769079","https://openalex.org/I889458895"]},{"raw_affiliation_string":"Department of Computer Science, Hong Kong University of Science and Technology, Hong Kong, P.R. China; E-mail: luhj@cs.ust.hk, , CN","institution_ids":["https://openalex.org/I200769079","https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002927193","display_name":"Wenyun Ji","orcid":null},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenyun Ji","raw_affiliation_strings":["Department of Computer Science, Fudan University, Shanghi, 200433, P.R. China;","Department of Computer Science, Fudan University, Shanghi, 200433, P.R. China; E-mail: {zptian, wyji, ayzhou}@fudan.edu.cn, CN"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Fudan University, Shanghi, 200433, P.R. China;","institution_ids":["https://openalex.org/I24943067"]},{"raw_affiliation_string":"Department of Computer Science, Fudan University, Shanghi, 200433, P.R. China; E-mail: {zptian, wyji, ayzhou}@fudan.edu.cn, CN","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101511862","display_name":"Aoying Zhou","orcid":"https://orcid.org/0000-0002-4665-7302"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Aoying Zhou","raw_affiliation_strings":["Department of Computer Science, Fudan University, Shanghi, 200433, P.R. China;","Department of Computer Science, Fudan University, Shanghi, 200433, P.R. China; E-mail: {zptian, wyji, ayzhou}@fudan.edu.cn, CN"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Fudan University, Shanghi, 200433, P.R. China;","institution_ids":["https://openalex.org/I24943067"]},{"raw_affiliation_string":"Department of Computer Science, Fudan University, Shanghi, 200433, P.R. China; E-mail: {zptian, wyji, ayzhou}@fudan.edu.cn, CN","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100831947","display_name":"Zhong Tian","orcid":null},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]},{"id":"https://openalex.org/I4210126794","display_name":"IBM Research (China)","ror":"https://ror.org/02yg1pf55","country_code":"CN","type":"company","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115","https://openalex.org/I4210126794"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhong Tian","raw_affiliation_strings":["Department of Computer Science, Fudan University, Shanghi, 200433, P.R. China;","IBM China Research Laboratory, Beijing, P.R. China;","IBM China Research Laboratory, Beijing, P.R. China; E-mail: tianz@cn.ibm.com, , CN"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Fudan University, Shanghi, 200433, P.R. China;","institution_ids":["https://openalex.org/I24943067"]},{"raw_affiliation_string":"IBM China Research Laboratory, Beijing, P.R. China;","institution_ids":["https://openalex.org/I4210126794"]},{"raw_affiliation_string":"IBM China Research Laboratory, Beijing, P.R. China; E-mail: tianz@cn.ibm.com, , CN","institution_ids":["https://openalex.org/I4210126794"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":2990,"currency":"USD","value_usd":2990},"apc_paid":null,"fwci":0.4299,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":{"value":0.67560801,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"3","issue":"4","first_page":"325","last_page":"331"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9973000288009644,"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9927999973297119,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8560230731964111},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.5103973746299744},{"id":"https://openalex.org/keywords/preprocessor","display_name":"Preprocessor","score":0.4931792616844177},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4834069311618805},{"id":"https://openalex.org/keywords/n-gram","display_name":"n-gram","score":0.45291706919670105},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.45232826471328735},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.44846612215042114},{"id":"https://openalex.org/keywords/sorting","display_name":"Sorting","score":0.4474942684173584},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.42809587717056274},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.42461422085762024},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.17979055643081665},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.14054980874061584}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8560230731964111},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.5103973746299744},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.4931792616844177},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4834069311618805},{"id":"https://openalex.org/C117884012","wikidata":"https://www.wikidata.org/wiki/Q94489","display_name":"n-gram","level":3,"score":0.45291706919670105},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.45232826471328735},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.44846612215042114},{"id":"https://openalex.org/C111696304","wikidata":"https://www.wikidata.org/wiki/Q2303697","display_name":"Sorting","level":2,"score":0.4474942684173584},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.42809587717056274},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.42461422085762024},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.17979055643081665},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.14054980874061584},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","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/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/s007990100044","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s007990100044","pdf_url":null,"source":{"id":"https://openalex.org/S110615584","display_name":"International Journal on Digital Libraries","issn_l":"1432-1300","issn":["1432-1300","1432-5012"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal on Digital Libraries","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W1484228408","https://openalex.org/W1500547548","https://openalex.org/W1569123402","https://openalex.org/W2010595692","https://openalex.org/W2019363722","https://openalex.org/W2020191321","https://openalex.org/W2023358833","https://openalex.org/W2024770506","https://openalex.org/W2052390074","https://openalex.org/W2073510489","https://openalex.org/W2087064593"],"related_works":["https://openalex.org/W2739612537","https://openalex.org/W2906970013","https://openalex.org/W2349174696","https://openalex.org/W2360241746","https://openalex.org/W4313041667","https://openalex.org/W2767599893","https://openalex.org/W3126081632","https://openalex.org/W2381572297","https://openalex.org/W2902593166","https://openalex.org/W1629127207"],"abstract_inverted_index":null,"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":1},{"year":2015,"cited_by_count":2},{"year":2012,"cited_by_count":2}],"updated_date":"2026-08-21T09:56:20.448147","created_date":"2025-10-10T00:00:00"}
