{"id":"https://openalex.org/W2208310611","doi":"https://doi.org/10.1109/bigdata.2015.7363781","title":"Big data entity resolution: From highly to somehow similar entity descriptions in the Web","display_name":"Big data entity resolution: From highly to somehow similar entity descriptions in the Web","publication_year":2015,"publication_date":"2015-10-01","ids":{"openalex":"https://openalex.org/W2208310611","doi":"https://doi.org/10.1109/bigdata.2015.7363781","mag":"2208310611"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata.2015.7363781","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata.2015.7363781","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE International Conference on Big Data (Big Data)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://inria.hal.science/hal-01199399","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5073440687","display_name":"Vasilis Efthymiou","orcid":"https://orcid.org/0000-0002-0683-030X"},"institutions":[{"id":"https://openalex.org/I142617266","display_name":"University of Crete","ror":"https://ror.org/00dr28g20","country_code":"GR","type":"education","lineage":["https://openalex.org/I142617266"]},{"id":"https://openalex.org/I4210121775","display_name":"FORTH Institute of Computer Science","ror":"https://ror.org/02tf48g55","country_code":"GR","type":"facility","lineage":["https://openalex.org/I4210121775","https://openalex.org/I8901234"]}],"countries":["GR"],"is_corresponding":true,"raw_author_name":"Vasilis Efthymiou","raw_affiliation_strings":["ICS-FORTH, Greece","University of Crete, Greece"],"affiliations":[{"raw_affiliation_string":"ICS-FORTH, Greece","institution_ids":["https://openalex.org/I4210121775"]},{"raw_affiliation_string":"University of Crete, Greece","institution_ids":["https://openalex.org/I142617266"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042740371","display_name":"Kostas Stefanidis","orcid":null},"institutions":[{"id":"https://openalex.org/I4210121775","display_name":"FORTH Institute of Computer Science","ror":"https://ror.org/02tf48g55","country_code":"GR","type":"facility","lineage":["https://openalex.org/I4210121775","https://openalex.org/I8901234"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Kostas Stefanidis","raw_affiliation_strings":["ICS-FORTH, Greece"],"affiliations":[{"raw_affiliation_string":"ICS-FORTH, Greece","institution_ids":["https://openalex.org/I4210121775"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5042003138","display_name":"Vassilis Christophides","orcid":"https://orcid.org/0000-0002-2076-1881"},"institutions":[{"id":"https://openalex.org/I1326498283","display_name":"Institut national de recherche en sciences et technologies du num\u00e9rique","ror":"https://ror.org/02kvxyf05","country_code":"FR","type":"government","lineage":["https://openalex.org/I1326498283"]},{"id":"https://openalex.org/I142617266","display_name":"University of Crete","ror":"https://ror.org/00dr28g20","country_code":"GR","type":"education","lineage":["https://openalex.org/I142617266"]}],"countries":["FR","GR"],"is_corresponding":false,"raw_author_name":"Vassilis Christophides","raw_affiliation_strings":["INRIA Paris-Rocquencourt, France","University of Crete, Greece"],"affiliations":[{"raw_affiliation_string":"INRIA Paris-Rocquencourt, France","institution_ids":["https://openalex.org/I1326498283"]},{"raw_affiliation_string":"University of Crete, Greece","institution_ids":["https://openalex.org/I142617266"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5073440687"],"corresponding_institution_ids":["https://openalex.org/I142617266","https://openalex.org/I4210121775"],"apc_list":null,"apc_paid":null,"fwci":7.4169,"has_fulltext":false,"cited_by_count":36,"citation_normalized_percentile":{"value":0.97063344,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"401","last_page":"410"},"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/T10215","display_name":"Semantic Web and Ontologies","score":0.9835000038146973,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9824000000953674,"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":0.8562872409820557},{"id":"https://openalex.org/keywords/blocking","display_name":"Blocking (statistics)","score":0.822790265083313},{"id":"https://openalex.org/keywords/pairwise-comparison","display_name":"Pairwise comparison","score":0.650341272354126},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5881752967834473},{"id":"https://openalex.org/keywords/block","display_name":"Block (permutation group theory)","score":0.5872225165367126},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5463848114013672},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.5144894123077393},{"id":"https://openalex.org/keywords/entity-linking","display_name":"Entity linking","score":0.511772096157074},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.40715521574020386},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.2846734821796417},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2300216257572174},{"id":"https://openalex.org/keywords/knowledge-base","display_name":"Knowledge base","score":0.11678382754325867}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8562872409820557},{"id":"https://openalex.org/C144745244","wikidata":"https://www.wikidata.org/wiki/Q4927286","display_name":"Blocking (statistics)","level":2,"score":0.822790265083313},{"id":"https://openalex.org/C184898388","wikidata":"https://www.wikidata.org/wiki/Q1435712","display_name":"Pairwise comparison","level":2,"score":0.650341272354126},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5881752967834473},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.5872225165367126},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5463848114013672},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.5144894123077393},{"id":"https://openalex.org/C96711827","wikidata":"https://www.wikidata.org/wiki/Q17012245","display_name":"Entity linking","level":3,"score":0.511772096157074},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.40715521574020386},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.2846734821796417},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2300216257572174},{"id":"https://openalex.org/C4554734","wikidata":"https://www.wikidata.org/wiki/Q593744","display_name":"Knowledge base","level":2,"score":0.11678382754325867},{"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/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","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},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/bigdata.2015.7363781","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata.2015.7363781","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE International Conference on Big Data (Big Data)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.706.7956","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.706.7956","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://users.ics.forth.gr/%7Ekstef/docs/bigdata15a.pdf","raw_type":"text"},{"id":"pmh:oai:HAL:hal-01199399v1","is_oa":true,"landing_page_url":"https://inria.hal.science/hal-01199399","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://cci.drexel.edu/bigdata/bigdata2015/","raw_type":"Conference papers"}],"best_oa_location":{"id":"pmh:oai:HAL:hal-01199399v1","is_oa":true,"landing_page_url":"https://inria.hal.science/hal-01199399","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://cci.drexel.edu/bigdata/bigdata2015/","raw_type":"Conference papers"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W140982117","https://openalex.org/W1981578383","https://openalex.org/W1981590391","https://openalex.org/W1986017822","https://openalex.org/W2005320059","https://openalex.org/W2011940398","https://openalex.org/W2049770245","https://openalex.org/W2089965140","https://openalex.org/W2096742765","https://openalex.org/W2101654853","https://openalex.org/W2104599107","https://openalex.org/W2109834209","https://openalex.org/W2145908616","https://openalex.org/W2152502401","https://openalex.org/W2158418361","https://openalex.org/W2216499221","https://openalex.org/W2323506184","https://openalex.org/W6605714439"],"related_works":["https://openalex.org/W2487162673","https://openalex.org/W2942366970","https://openalex.org/W2793211469","https://openalex.org/W2949152769","https://openalex.org/W4372354731","https://openalex.org/W2562400057","https://openalex.org/W1692008701","https://openalex.org/W2010725720","https://openalex.org/W4310066305","https://openalex.org/W2099811626"],"abstract_inverted_index":{"In":[0,17],"the":[1,15,26,36,42,74,84,94,104,107],"Web":[2,27,85],"of":[3,28,45,86,98,106,116],"data,":[4,29],"entities":[5],"are":[6],"described":[7],"by":[8],"interlinked":[9],"data":[10,87],"rather":[11],"than":[12],"documents":[13],"on":[14,22],"Web.":[16],"this":[18],"work,":[19],"we":[20,102],"focus":[21],"entity":[23,50,63,110],"resolution":[24,51],"in":[25],"i.e.,":[30],"identifying":[31],"descriptions":[32,64,72,111],"that":[33,92,118],"refer":[34],"to":[35],"same":[37,75],"real-world":[38],"entity.":[39],"To":[40],"reduce":[41],"required":[43],"number":[44],"pairwise":[46],"comparisons,":[47],"methods":[48],"for":[49,83],"perform":[52],"blocking":[53,59,80,119],"as":[54],"a":[55],"pre-processing":[56],"step.":[57],"A":[58],"technique":[60],"places":[61],"similar":[62],"into":[65],"blocks":[66],"and":[67,88,96,112],"executes":[68],"comparisons":[69],"only":[70],"between":[71],"within":[73],"block.":[76],"We":[77],"experimentally":[78],"evaluate":[79],"techniques":[81,120],"proposed":[82],"present":[89],"dataset":[90],"characteristics":[91,105],"determine":[93],"effectiveness":[95],"efficiency":[97],"such":[99],"methods.":[100],"Furthermore,":[101],"analyze":[103],"missed":[108],"matching":[109],"examine":[113],"different":[114],"types":[115],"links":[117],"can":[121],"potentially":[122],"identify.":[123]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":6},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":7},{"year":2016,"cited_by_count":6},{"year":2015,"cited_by_count":1}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}