{"id":"https://openalex.org/W3014689699","doi":"https://doi.org/10.1145/3341105.3375776","title":"Schema-agnostic blocking for streaming data","display_name":"Schema-agnostic blocking for streaming data","publication_year":2020,"publication_date":"2020-03-29","ids":{"openalex":"https://openalex.org/W3014689699","doi":"https://doi.org/10.1145/3341105.3375776","mag":"3014689699"},"language":"en","primary_location":{"id":"doi:10.1145/3341105.3375776","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3341105.3375776","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 35th Annual ACM Symposium on Applied Computing","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/A5040142167","display_name":"Tiago Brasileiro Ara\u00fajo","orcid":"https://orcid.org/0000-0001-6339-9117"},"institutions":[{"id":"https://openalex.org/I41455075","display_name":"Universidade Federal de Campina Grande","ror":"https://ror.org/00eftnx64","country_code":"BR","type":"education","lineage":["https://openalex.org/I41455075"]}],"countries":["BR"],"is_corresponding":true,"raw_author_name":"Tiago Brasileiro Ara\u00fajo","raw_affiliation_strings":["Federal University of Campina Grande, Campina Grande, Brazil"],"affiliations":[{"raw_affiliation_string":"Federal University of Campina Grande, Campina Grande, Brazil","institution_ids":["https://openalex.org/I41455075"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042740371","display_name":"Kostas Stefanidis","orcid":"https://orcid.org/0000-0003-1317-8062"},"institutions":[{"id":"https://openalex.org/I166825849","display_name":"Tampere University","ror":"https://ror.org/033003e23","country_code":"FI","type":"education","lineage":["https://openalex.org/I166825849"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Kostas Stefanidis","raw_affiliation_strings":["Tampere University, Tampere, Finland"],"affiliations":[{"raw_affiliation_string":"Tampere University, Tampere, Finland","institution_ids":["https://openalex.org/I166825849"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040330943","display_name":"Carlos Eduardo Santos Pires","orcid":"https://orcid.org/0000-0001-7743-899X"},"institutions":[{"id":"https://openalex.org/I41455075","display_name":"Universidade Federal de Campina Grande","ror":"https://ror.org/00eftnx64","country_code":"BR","type":"education","lineage":["https://openalex.org/I41455075"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Carlos Eduardo Santos Pires","raw_affiliation_strings":["Federal University of Campina Grande, Campina Grande, Brazil"],"affiliations":[{"raw_affiliation_string":"Federal University of Campina Grande, Campina Grande, Brazil","institution_ids":["https://openalex.org/I41455075"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045034530","display_name":"Jyrki Nummenmaa","orcid":"https://orcid.org/0000-0002-7476-7840"},"institutions":[{"id":"https://openalex.org/I166825849","display_name":"Tampere University","ror":"https://ror.org/033003e23","country_code":"FI","type":"education","lineage":["https://openalex.org/I166825849"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Jyrki Nummenmaa","raw_affiliation_strings":["Tampere University, Tampere, Finland"],"affiliations":[{"raw_affiliation_string":"Tampere University, Tampere, Finland","institution_ids":["https://openalex.org/I166825849"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5088926017","display_name":"Thiago N\u00f3brega","orcid":"https://orcid.org/0000-0001-7532-2109"},"institutions":[{"id":"https://openalex.org/I136754270","display_name":"Universidade Estadual da Para\u00edba","ror":"https://ror.org/02cm65z11","country_code":"BR","type":"education","lineage":["https://openalex.org/I136754270"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Thiago Pereira da N\u00f3brega","raw_affiliation_strings":["State University of Para\u00edba, Campina Grande, Brazil"],"affiliations":[{"raw_affiliation_string":"State University of Para\u00edba, Campina Grande, Brazil","institution_ids":["https://openalex.org/I136754270"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5040142167"],"corresponding_institution_ids":["https://openalex.org/I41455075"],"apc_list":null,"apc_paid":null,"fwci":1.109,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.79921668,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"412","last_page":"419"},"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/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.9940999746322632,"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/T11614","display_name":"Cloud Data Security Solutions","score":0.9925000071525574,"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":0.8441811800003052},{"id":"https://openalex.org/keywords/schema","display_name":"Schema (genetic algorithms)","score":0.7006345987319946},{"id":"https://openalex.org/keywords/blocking","display_name":"Blocking (statistics)","score":0.6716497540473938},{"id":"https://openalex.org/keywords/block","display_name":"Block (permutation group theory)","score":0.5505046844482422},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.4471658170223236},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.43625447154045105},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.23772484064102173},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.18999207019805908},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.11624962091445923}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8441811800003052},{"id":"https://openalex.org/C52146309","wikidata":"https://www.wikidata.org/wiki/Q7431116","display_name":"Schema (genetic algorithms)","level":2,"score":0.7006345987319946},{"id":"https://openalex.org/C144745244","wikidata":"https://www.wikidata.org/wiki/Q4927286","display_name":"Blocking (statistics)","level":2,"score":0.6716497540473938},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.5505046844482422},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.4471658170223236},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.43625447154045105},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.23772484064102173},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.18999207019805908},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.11624962091445923},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3341105.3375776","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3341105.3375776","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 35th Annual ACM Symposium on Applied Computing","raw_type":"proceedings-article"},{"id":"pmh:oai:trepo.tuni.fi:10024/216317","is_oa":false,"landing_page_url":"https://trepo.tuni.fi/handle/10024/216317","pdf_url":null,"source":{"id":"https://openalex.org/S7407055260","display_name":"Trepo - Institutional Repository of Tampere University","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":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"conference"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9","score":0.6499999761581421}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W1504263697","https://openalex.org/W2261544779","https://openalex.org/W2342256727","https://openalex.org/W2398333000","https://openalex.org/W2406045281","https://openalex.org/W2559870814","https://openalex.org/W2566927129","https://openalex.org/W2614359430","https://openalex.org/W2727352725","https://openalex.org/W2772790565","https://openalex.org/W2911949487","https://openalex.org/W2933781133","https://openalex.org/W2943447120","https://openalex.org/W2980624060","https://openalex.org/W4231155644"],"related_works":["https://openalex.org/W2392835431","https://openalex.org/W2126932387","https://openalex.org/W1965371215","https://openalex.org/W2032233321","https://openalex.org/W2353762239","https://openalex.org/W3121970507","https://openalex.org/W2185938410","https://openalex.org/W2110028391","https://openalex.org/W54497855","https://openalex.org/W2484966135"],"abstract_inverted_index":{"Currently,":[0],"a":[1,8,28,100],"wide":[2],"number":[3],"of":[4,11,45],"information":[5],"systems":[6],"produce":[7],"large":[9,68],"amount":[10],"data":[12,65,69,87,125],"continuously.":[13],"Since":[14],"these":[15,77,93],"sources":[16],"may":[17],"have":[18],"overlapping":[19],"knowledge,":[20],"the":[21,42,46,141],"Entity":[22],"Resolution":[23],"(ER)":[24],"task":[25],"emerges":[26],"as":[27],"fundamental":[29],"step":[30],"to":[31,54,64,113,140],"integrate":[32],"multiple":[33],"knowledge":[34],"bases":[35],"or":[36],"identify":[37],"similarities":[38],"between":[39],"entities.":[40],"Considering":[41],"quadratic":[43],"cost":[44],"ER":[47],"task,":[48],"blocking":[49,79,104,115],"techniques":[50,58,80],"are":[51],"often":[52],"used":[53],"improve":[55],"efficiency.":[56,116],"Such":[57],"face":[59,82],"two":[60,83],"main":[61],"challenges":[62,95],"related":[63],"volume":[66],"(i.e.,":[67,73],"sources)":[70],"and":[71,88,128,137],"variety":[72],"heterogeneous":[74],"data).":[75],"Besides":[76],"challenges,":[78],"also":[81],"other":[84],"ones:":[85],"streaming":[86],"incremental":[89,102],"processing.":[90],"To":[91],"address":[92],"four":[94,123],"simultaneously,":[96],"we":[97,121],"propose":[98],"PI-Block,":[99],"novel":[101],"schema-agnostic":[103],"technique":[105],"that":[106,130],"utilizes":[107],"parallelism":[108],"(through":[109],"distributed":[110],"computational":[111],"infrastructure)":[112],"enhance":[114],"In":[117],"our":[118],"experimental":[119],"evaluation,":[120],"use":[122],"real-world":[124],"source":[126],"pairs,":[127],"highlight":[129],"PI-Block":[131],"achieves":[132],"better":[133],"results":[134],"regarding":[135],"efficiency":[136],"effectiveness":[138],"compared":[139],"state-of-the-art":[142],"technique.":[143]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1}],"updated_date":"2026-03-06T13:50:29.536080","created_date":"2025-10-10T00:00:00"}
