{"id":"https://openalex.org/W2535168187","doi":"https://doi.org/10.14778/2994509.2994533","title":"BLAST","display_name":"BLAST","publication_year":2016,"publication_date":"2016-08-01","ids":{"openalex":"https://openalex.org/W2535168187","doi":"https://doi.org/10.14778/2994509.2994533","mag":"2535168187"},"language":"en","primary_location":{"id":"doi:10.14778/2994509.2994533","is_oa":false,"landing_page_url":"https://doi.org/10.14778/2994509.2994533","pdf_url":null,"source":{"id":"https://openalex.org/S4210226185","display_name":"Proceedings of the VLDB Endowment","issn_l":"2150-8097","issn":["2150-8097"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the VLDB Endowment","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://www.vldb.org/pvldb/vol9/p1173-simonini.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5047630333","display_name":"Giovanni Simonini","orcid":"https://orcid.org/0000-0002-3466-509X"},"institutions":[{"id":"https://openalex.org/I122346577","display_name":"University of Modena and Reggio Emilia","ror":"https://ror.org/02d4c4y02","country_code":"IT","type":"education","lineage":["https://openalex.org/I122346577"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Giovanni Simonini","raw_affiliation_strings":["Universit\u00e0 degli Studi di, Modena e Reggio Emilia, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universit\u00e0 degli Studi di, Modena e Reggio Emilia, Italy","institution_ids":["https://openalex.org/I122346577"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037830808","display_name":"Sonia Bergamaschi","orcid":"https://orcid.org/0000-0001-8087-6587"},"institutions":[{"id":"https://openalex.org/I122346577","display_name":"University of Modena and Reggio Emilia","ror":"https://ror.org/02d4c4y02","country_code":"IT","type":"education","lineage":["https://openalex.org/I122346577"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Sonia Bergamaschi","raw_affiliation_strings":["Universit\u00e0 degli Studi di, Modena e Reggio Emilia, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universit\u00e0 degli Studi di, Modena e Reggio Emilia, Italy","institution_ids":["https://openalex.org/I122346577"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5090550596","display_name":"H. V. Jagadish","orcid":"https://orcid.org/0000-0003-0724-5214"},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"H. V. Jagadish","raw_affiliation_strings":["Univ. of Michigan, Ann Arbor"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Univ. of Michigan, Ann Arbor","institution_ids":["https://openalex.org/I27837315"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":11.5691,"has_fulltext":true,"cited_by_count":68,"citation_normalized_percentile":{"value":0.98515979,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":100},"biblio":{"volume":"9","issue":"12","first_page":"1173","last_page":"1184"},"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":0.9940999746322632,"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/T10317","display_name":"Advanced Database Systems and Queries","score":0.9929999709129333,"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":0.8353430032730103},{"id":"https://openalex.org/keywords/schema","display_name":"Schema (genetic algorithms)","score":0.5708732008934021},{"id":"https://openalex.org/keywords/redundancy","display_name":"Redundancy (engineering)","score":0.5368417501449585},{"id":"https://openalex.org/keywords/blocking","display_name":"Blocking (statistics)","score":0.5209485292434692},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5022850036621094},{"id":"https://openalex.org/keywords/data-integration","display_name":"Data integration","score":0.4404812455177307},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3334989845752716},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3328845500946045}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8353430032730103},{"id":"https://openalex.org/C52146309","wikidata":"https://www.wikidata.org/wiki/Q7431116","display_name":"Schema (genetic algorithms)","level":2,"score":0.5708732008934021},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.5368417501449585},{"id":"https://openalex.org/C144745244","wikidata":"https://www.wikidata.org/wiki/Q4927286","display_name":"Blocking (statistics)","level":2,"score":0.5209485292434692},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5022850036621094},{"id":"https://openalex.org/C72634772","wikidata":"https://www.wikidata.org/wiki/Q386824","display_name":"Data integration","level":2,"score":0.4404812455177307},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3334989845752716},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3328845500946045},{"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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.14778/2994509.2994533","is_oa":false,"landing_page_url":"https://doi.org/10.14778/2994509.2994533","pdf_url":null,"source":{"id":"https://openalex.org/S4210226185","display_name":"Proceedings of the VLDB Endowment","issn_l":"2150-8097","issn":["2150-8097"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the VLDB Endowment","raw_type":"journal-article"},{"id":"pmh:oai:iris.unimore.it:11380/1111659","is_oa":true,"landing_page_url":"http://hdl.handle.net/11380/1111659","pdf_url":"http://www.vldb.org/pvldb/vol9/p1173-simonini.pdf","source":{"id":"https://openalex.org/S4306400718","display_name":"IRIS UNIMORE (University of Modena and Reggio Emilia)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I122346577","host_organization_name":"University of Modena and Reggio Emilia","host_organization_lineage":["https://openalex.org/I122346577"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"pmh:oai:iris.unimore.it:11380/1111659","is_oa":true,"landing_page_url":"http://hdl.handle.net/11380/1111659","pdf_url":"http://www.vldb.org/pvldb/vol9/p1173-simonini.pdf","source":{"id":"https://openalex.org/S4306400718","display_name":"IRIS UNIMORE (University of Modena and Reggio Emilia)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I122346577","host_organization_name":"University of Modena and Reggio Emilia","host_organization_lineage":["https://openalex.org/I122346577"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2535168187.pdf","grobid_xml":"https://content.openalex.org/works/W2535168187.grobid-xml"},"referenced_works_count":28,"referenced_works":["https://openalex.org/W192652968","https://openalex.org/W343945789","https://openalex.org/W1556911442","https://openalex.org/W1736726159","https://openalex.org/W1995099886","https://openalex.org/W2013093146","https://openalex.org/W2015191210","https://openalex.org/W2027393969","https://openalex.org/W2031250218","https://openalex.org/W2036216970","https://openalex.org/W2099111195","https://openalex.org/W2101654853","https://openalex.org/W2104511295","https://openalex.org/W2132069633","https://openalex.org/W2132658991","https://openalex.org/W2139490252","https://openalex.org/W2152502401","https://openalex.org/W2161936973","https://openalex.org/W2210065635","https://openalex.org/W2323506184","https://openalex.org/W2346919594","https://openalex.org/W2398333000","https://openalex.org/W2407779602","https://openalex.org/W3148106702","https://openalex.org/W4237638794","https://openalex.org/W6674851815","https://openalex.org/W6683401941","https://openalex.org/W6714048071"],"related_works":["https://openalex.org/W2392835431","https://openalex.org/W1965371215","https://openalex.org/W2126932387","https://openalex.org/W1842396145","https://openalex.org/W2353762239","https://openalex.org/W2108990487","https://openalex.org/W2484966135","https://openalex.org/W2015050211","https://openalex.org/W2126435977","https://openalex.org/W2017131087"],"abstract_inverted_index":{"Identifying":[0],"records":[1,41,49],"that":[2,137],"refer":[3],"to":[4,20,31,48,55,74,123,141,178],"the":[5,33,46,67,76,83,118,125,128,191,201],"same":[6],"entity":[7],"is":[8,17,82],"a":[9,52,131,172],"fundamental":[10],"step":[11,174],"for":[12,175],"data":[13,62,65],"integration.":[14],"Since":[15],"it":[16,151],"prohibitively":[18],"expensive":[19],"compare":[21],"every":[22],"pair":[23],"of":[24,35,66,78,85,127],"records,":[25],"blocking":[26,91],"techniques":[27,39,70],"are":[28],"typically":[29],"employed":[30],"reduce":[32,75],"complexity":[34],"this":[36,105,167],"task.":[37],"These":[38],"partition":[40],"into":[42],"blocks":[43,87,129],"and":[44,60],"limit":[45],"comparison":[47],"co-occurring":[50],"in":[51,130,197],"block.":[53],"Generally,":[54],"deal":[56],"with":[57,155],"highly":[58],"heterogeneous":[59],"noisy":[61],"(e.g.":[63],"semi-structured":[64],"Web),":[68],"these":[69],"rely":[71,99],"on":[72,101,184],"redundancy":[73],"chance":[77],"missing":[79],"matches.":[80],"Meta-blocking":[81],"task":[84],"restructuring":[86],"generated":[88],"by":[89,170],"redundancy-based":[90],"techniques,":[92],"removing":[93],"superfluous":[94],"comparisons.":[95],"Existing":[96],"meta-blocking":[97,194],"approaches":[98],"exclusively":[100],"schema-agnostic":[102],"features.":[103],"In":[104],"paper,":[106],"we":[107],"demonstrate":[108],"how":[109,161,187],"\"loose\"":[110],"schema":[111],"information":[112,169],"(i.e.,":[113],"statistics":[114],"collected":[115],"directly":[116],"from":[117],"data)":[119],"can":[120,138,164],"be":[121,139],"exploited":[122],"enhance":[124],"quality":[126],"holistic":[132],"loosely":[133],"schema-aware":[134],"(meta-)blocking":[135],"approach":[136],"used":[140],"speed":[142],"up":[143],"your":[144],"favorite":[145],"Entity":[146],"Resolution":[147],"algorithm.":[148],"We":[149,159,181],"call":[150],"B":[152,162,188],"last":[153,163,189],"(Blocking":[154],"Loosely-Aware":[156],"Schema":[157],"Techniques).":[158],"show":[160],"automatically":[165],"extract":[166],"loose":[168],"adopting":[171],"LSH-based":[173],"efficiently":[176],"scaling":[177],"large":[179],"datasets.":[180],"experimentally":[182],"demonstrate,":[183],"real-world":[185],"datasets,":[186],"outperforms":[190],"state-of-the-art":[192],"unsupervised":[193],"approaches,":[195],"and,":[196],"many":[198],"cases,":[199],"also":[200],"supervised":[202],"one.":[203]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":11},{"year":2020,"cited_by_count":9},{"year":2019,"cited_by_count":8},{"year":2018,"cited_by_count":14},{"year":2017,"cited_by_count":8},{"year":2016,"cited_by_count":2}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2016-10-28T00:00:00"}