{"id":"https://openalex.org/W2903096023","doi":"https://doi.org/10.1109/icacci.2018.8554946","title":"On Evaluation of Entity Matching Techniques for Bibliographic Database","display_name":"On Evaluation of Entity Matching Techniques for Bibliographic Database","publication_year":2018,"publication_date":"2018-09-01","ids":{"openalex":"https://openalex.org/W2903096023","doi":"https://doi.org/10.1109/icacci.2018.8554946","mag":"2903096023"},"language":"en","primary_location":{"id":"doi:10.1109/icacci.2018.8554946","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icacci.2018.8554946","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 International Conference on Advances in Computing, Communications and Informatics (ICACCI)","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/A5021971352","display_name":"Sumit Mishra","orcid":"https://orcid.org/0000-0001-9333-2001"},"institutions":[{"id":"https://openalex.org/I4210089896","display_name":"Indian Institute of Information Technology Guwahati","ror":"https://ror.org/00bb9ch64","country_code":"IN","type":"education","lineage":["https://openalex.org/I4210089896"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Sumit Mishra","raw_affiliation_strings":["Department of CSE, Indian Institute of Information Technology, Guwahati, Assam, India"],"affiliations":[{"raw_affiliation_string":"Department of CSE, Indian Institute of Information Technology, Guwahati, Assam, India","institution_ids":["https://openalex.org/I4210089896"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060797340","display_name":"Sriparna Saha","orcid":"https://orcid.org/0000-0001-5458-9381"},"institutions":[{"id":"https://openalex.org/I132153292","display_name":"Indian Institute of Technology Patna","ror":"https://ror.org/01ft5vz71","country_code":"IN","type":"education","lineage":["https://openalex.org/I132153292"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Sriparna Saha","raw_affiliation_strings":["Department of CSE, Indian Institute of Technology, Patna, Bihar, India"],"affiliations":[{"raw_affiliation_string":"Department of CSE, Indian Institute of Technology, Patna, Bihar, India","institution_ids":["https://openalex.org/I132153292"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5088675403","display_name":"Samrat Mondal","orcid":"https://orcid.org/0000-0002-2159-3410"},"institutions":[{"id":"https://openalex.org/I132153292","display_name":"Indian Institute of Technology Patna","ror":"https://ror.org/01ft5vz71","country_code":"IN","type":"education","lineage":["https://openalex.org/I132153292"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Samrat Mondal","raw_affiliation_strings":["Department of CSE, Indian Institute of Technology, Patna, Bihar, India"],"affiliations":[{"raw_affiliation_string":"Department of CSE, Indian Institute of Technology, Patna, Bihar, India","institution_ids":["https://openalex.org/I132153292"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5021971352"],"corresponding_institution_ids":["https://openalex.org/I4210089896"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.17639386,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"24","issue":null,"first_page":"2325","last_page":"2331"},"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/T11819","display_name":"Data-Driven Disease Surveillance","score":0.9799000024795532,"subfield":{"id":"https://openalex.org/subfields/2713","display_name":"Epidemiology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9659000039100647,"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/correctness","display_name":"Correctness","score":0.868478536605835},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8450628519058228},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.70859295129776},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6171956658363342},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.6107035875320435},{"id":"https://openalex.org/keywords/measure","display_name":"Measure (data warehouse)","score":0.5021584033966064},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.3664657473564148},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.10073786973953247}],"concepts":[{"id":"https://openalex.org/C55439883","wikidata":"https://www.wikidata.org/wiki/Q360812","display_name":"Correctness","level":2,"score":0.868478536605835},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8450628519058228},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.70859295129776},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6171956658363342},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.6107035875320435},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.5021584033966064},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.3664657473564148},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.10073786973953247},{"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:10.1109/icacci.2018.8554946","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icacci.2018.8554946","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 International Conference on Advances in Computing, Communications and Informatics (ICACCI)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W106880317","https://openalex.org/W149565845","https://openalex.org/W175950377","https://openalex.org/W178573792","https://openalex.org/W1874194247","https://openalex.org/W1977340740","https://openalex.org/W2022322548","https://openalex.org/W2024770506","https://openalex.org/W2082696804","https://openalex.org/W2090365396","https://openalex.org/W2104051689","https://openalex.org/W2108323654","https://openalex.org/W2120623936","https://openalex.org/W2136517229","https://openalex.org/W2145893390","https://openalex.org/W2500925358","https://openalex.org/W2559636315","https://openalex.org/W2594541096","https://openalex.org/W2594735838","https://openalex.org/W2602953083","https://openalex.org/W2610904283","https://openalex.org/W2749557108","https://openalex.org/W3212067219","https://openalex.org/W4254788633","https://openalex.org/W6604335697","https://openalex.org/W6639027110","https://openalex.org/W6736139338","https://openalex.org/W6803514084"],"related_works":["https://openalex.org/W1667647204","https://openalex.org/W2404647514","https://openalex.org/W4247536566","https://openalex.org/W4241418540","https://openalex.org/W2018477250","https://openalex.org/W3119814709","https://openalex.org/W1508895727","https://openalex.org/W2725786787","https://openalex.org/W1875930651","https://openalex.org/W1590965489"],"abstract_inverted_index":{"In":[0,104],"entity":[1,18,101,135],"matching":[2,102,136],"techniques":[3,29],"from":[4,73],"bibliographic":[5,109],"databases":[6],"like":[7],"DBLP,":[8],"Arnetminer,":[9],"Scopus,":[10],"Google":[11],"Scholar,":[12],"etc.,":[13],"records":[14],"of":[15,27,89,99,124,146],"the":[16,25,61,71,81,87,97,100,108,122],"same":[17],"need":[19],"to":[20,45,95,106,130],"be":[21],"clustered":[22],"together.":[23],"Checking":[24],"correctness":[26,52],"such":[28],"is":[30,49,65,140],"very":[31,43,66],"challenging":[32],"because":[33],"actual":[34],"or":[35,42],"correct":[36],"results":[37],"are":[38,115,119],"often":[39],"not":[40],"known":[41],"difficult":[44],"know.":[46],"Generally,":[47],"F-measure":[48],"used":[50,116],"for":[51,134],"evaluation,":[53],"which":[54],"requires":[55,70],"gold":[56,62],"standard":[57,63],"data.":[58],"However,":[59],"obtaining":[60],"data":[64,147],"difficult,":[67],"time-consuming":[68],"and":[69,117],"help":[72],"some":[74,90],"human-annotators.":[75],"To":[76],"address":[77],"this":[78],"problem,":[79],"in":[80],"current":[82],"work,":[83],"we":[84],"have":[85],"proposed":[86],"use":[88],"internal":[91,126,151],"cluster":[92,127],"validity":[93,128,152],"measures":[94,114,129],"evaluate":[96],"goodness":[98],"techniques.":[103],"order":[105],"handle":[107],"databases,":[110],"several":[111],"different":[112],"distance":[113],"these":[118],"incorporated":[120],"into":[121],"definitions":[123],"various":[125,150],"make":[131],"them":[132],"applicable":[133],"problem.":[137],"Comparative":[138],"analysis":[139],"done":[141],"on":[142],"a":[143],"large":[144],"collection":[145],"sets":[148],"considering":[149],"measures.":[153]},"counts_by_year":[],"updated_date":"2026-04-05T06:14:27.290980","created_date":"2025-10-10T00:00:00"}
