{"id":"https://openalex.org/W2980624060","doi":"https://doi.org/10.1145/3350546.3352542","title":"Incremental Blocking for Entity Resolution over Web Streaming Data","display_name":"Incremental Blocking for Entity Resolution over Web Streaming Data","publication_year":2019,"publication_date":"2019-10-14","ids":{"openalex":"https://openalex.org/W2980624060","doi":"https://doi.org/10.1145/3350546.3352542","mag":"2980624060"},"language":"en","primary_location":{"id":"doi:10.1145/3350546.3352542","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3350546.3352542","pdf_url":null,"source":{"id":"https://openalex.org/S4363608074","display_name":"IEEE/WIC/ACM International Conference on Web Intelligence","issn_l":null,"issn":null,"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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/WIC/ACM International Conference on Web Intelligence","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://trepo.tuni.fi/bitstream/10024/118526/2/Incremental_Blocking_for_2019.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5040142167","display_name":"Tiago Brasileiro Ara\u00fajo","orcid":"https://orcid.org/0000-0001-6339-9117"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Tiago Brasileiro Ara\u00fajo","raw_affiliation_strings":["UFCG/TUNI, Brazil"],"affiliations":[{"raw_affiliation_string":"UFCG/TUNI, Brazil","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042740371","display_name":"Kostas Stefanidis","orcid":"https://orcid.org/0000-0003-1317-8062"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kostas Stefanidis","raw_affiliation_strings":["TUNI, Finland"],"affiliations":[{"raw_affiliation_string":"TUNI, Finland","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040330943","display_name":"Carlos Eduardo Santos Pires","orcid":"https://orcid.org/0000-0001-7743-899X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Carlos Eduardo Santos Pires","raw_affiliation_strings":["UFCG, Brazil"],"affiliations":[{"raw_affiliation_string":"UFCG, Brazil","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045034530","display_name":"Jyrki Nummenmaa","orcid":"https://orcid.org/0000-0002-7476-7840"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jyrki Nummenmaa","raw_affiliation_strings":["TUNI, Finland"],"affiliations":[{"raw_affiliation_string":"TUNI, Finland","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5088926017","display_name":"Thiago N\u00f3brega","orcid":"https://orcid.org/0000-0001-7532-2109"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Thiago Pereira da N\u00f3brega","raw_affiliation_strings":["UFCG, Brazil"],"affiliations":[{"raw_affiliation_string":"UFCG, Brazil","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5040142167"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.8015,"has_fulltext":true,"cited_by_count":5,"citation_normalized_percentile":{"value":0.70875421,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"332","last_page":"336"},"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/T10772","display_name":"Distributed systems and fault tolerance","score":0.9933000206947327,"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"}},{"id":"https://openalex.org/T10317","display_name":"Advanced Database Systems and Queries","score":0.9922999739646912,"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":0.8750884532928467},{"id":"https://openalex.org/keywords/blocking","display_name":"Blocking (statistics)","score":0.7048641443252563},{"id":"https://openalex.org/keywords/schema","display_name":"Schema (genetic algorithms)","score":0.585214376449585},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.46497249603271484},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.4485253393650055},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.32089945673942566},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.21992382407188416},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.15620553493499756}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8750884532928467},{"id":"https://openalex.org/C144745244","wikidata":"https://www.wikidata.org/wiki/Q4927286","display_name":"Blocking (statistics)","level":2,"score":0.7048641443252563},{"id":"https://openalex.org/C52146309","wikidata":"https://www.wikidata.org/wiki/Q7431116","display_name":"Schema (genetic algorithms)","level":2,"score":0.585214376449585},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.46497249603271484},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.4485253393650055},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.32089945673942566},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.21992382407188416},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.15620553493499756},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3350546.3352542","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3350546.3352542","pdf_url":null,"source":{"id":"https://openalex.org/S4363608074","display_name":"IEEE/WIC/ACM International Conference on Web Intelligence","issn_l":null,"issn":null,"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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/WIC/ACM International Conference on Web Intelligence","raw_type":"proceedings-article"},{"id":"pmh:oai:trepo.tuni.fi:10024/118526","is_oa":true,"landing_page_url":"https://trepo.tuni.fi/handle/10024/118526","pdf_url":"https://trepo.tuni.fi/bitstream/10024/118526/2/Incremental_Blocking_for_2019.pdf","source":{"id":"https://openalex.org/S4306401860","display_name":"Tampere University Institutional Repository (Tampere University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I150589677","host_organization_name":"Tampere University of Applied Sciences","host_organization_lineage":["https://openalex.org/I150589677"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"acceptedVersion"}],"best_oa_location":{"id":"pmh:oai:trepo.tuni.fi:10024/118526","is_oa":true,"landing_page_url":"https://trepo.tuni.fi/handle/10024/118526","pdf_url":"https://trepo.tuni.fi/bitstream/10024/118526/2/Incremental_Blocking_for_2019.pdf","source":{"id":"https://openalex.org/S4306401860","display_name":"Tampere University Institutional Repository (Tampere University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I150589677","host_organization_name":"Tampere University of Applied Sciences","host_organization_lineage":["https://openalex.org/I150589677"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"acceptedVersion"},"sustainable_development_goals":[{"score":0.6200000047683716,"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2980624060.pdf","grobid_xml":"https://content.openalex.org/works/W2980624060.grobid-xml"},"referenced_works_count":14,"referenced_works":["https://openalex.org/W1504263697","https://openalex.org/W1547612978","https://openalex.org/W1995099886","https://openalex.org/W2261544779","https://openalex.org/W2398333000","https://openalex.org/W2535168187","https://openalex.org/W2559870814","https://openalex.org/W2594063363","https://openalex.org/W2614359430","https://openalex.org/W2727352725","https://openalex.org/W2750964846","https://openalex.org/W2772790565","https://openalex.org/W2933781133","https://openalex.org/W4231155644"],"related_works":["https://openalex.org/W2392835431","https://openalex.org/W2126932387","https://openalex.org/W1965371215","https://openalex.org/W2353762239","https://openalex.org/W2185938410","https://openalex.org/W2484966135","https://openalex.org/W2015050211","https://openalex.org/W2108990487","https://openalex.org/W1978276953","https://openalex.org/W2353899468"],"abstract_inverted_index":{"The":[0,95],"widespread":[1],"use":[2],"of":[3,11],"information":[4],"systems":[5],"has":[6],"become":[7],"a":[8,22,82,105,119],"valuable":[9],"source":[10],"semi-structured":[12],"data.":[13],"In":[14],"this":[15],"context,":[16],"Entity":[17],"Resolution":[18],"(ER)":[19],"emerges":[20],"as":[21],"fundamental":[23],"task":[24],"to":[25,50,57,91,123],"integrate":[26],"multiple":[27],"knowledge":[28],"bases":[29],"or":[30],"identify":[31],"similarities":[32],"between":[33],"data":[34,59,71,103],"items":[35],"(i.e.,":[36],"entities).":[37],"Since":[38],"ER":[39],"is":[40],"an":[41],"inherently":[42],"quadratic":[43],"task,":[44],"blocking":[45,63,86,93],"techniques":[46,64],"are":[47],"often":[48],"used":[49],"improve":[51,110],"efficiency.":[52,94],"Beyond":[53],"the":[54,58,112],"challenges":[55],"related":[56],"volume":[60],"and":[61,72,101,117],"heterogeneity,":[62],"also":[65],"face":[66],"two":[67],"other":[68],"challenges:":[69],"streaming":[70,100],"incremental":[73,84,102],"processing.":[74],"To":[75,109],"address":[76],"these":[77],"challenges,":[78],"we":[79],"propose":[80],"PRIME,":[81],"novel":[83],"schema-agnostic":[85],"technique":[87,97,113],"that":[88],"utilizes":[89],"parallelism":[90],"enhance":[92],"proposed":[96],"deals":[98],"with":[99],"using":[104],"distributed":[106],"computational":[107],"infrastructure.":[108],"efficiency,":[111],"avoids":[114],"unnecessary":[115],"comparisons":[116],"applies":[118],"time":[120],"window":[121],"strategy":[122],"prevent":[124],"excessive":[125],"memory":[126],"consumption.":[127]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2020,"cited_by_count":2}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}
