{"id":"https://openalex.org/W3137713953","doi":"https://doi.org/10.3390/info12030134","title":"Unsupervised DNF Blocking for Efficient Linking of Knowledge Graphs and Tables","display_name":"Unsupervised DNF Blocking for Efficient Linking of Knowledge Graphs and Tables","publication_year":2021,"publication_date":"2021-03-19","ids":{"openalex":"https://openalex.org/W3137713953","doi":"https://doi.org/10.3390/info12030134","mag":"3137713953"},"language":"en","primary_location":{"id":"doi:10.3390/info12030134","is_oa":true,"landing_page_url":"https://doi.org/10.3390/info12030134","pdf_url":"https://www.mdpi.com/2078-2489/12/3/134/pdf?version=1616148415","source":{"id":"https://openalex.org/S4210219776","display_name":"Information","issn_l":"2078-2489","issn":["2078-2489"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Information","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.mdpi.com/2078-2489/12/3/134/pdf?version=1616148415","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5074197492","display_name":"Mayank Kejriwal","orcid":"https://orcid.org/0000-0001-5988-8305"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Mayank Kejriwal","raw_affiliation_strings":["Information Sciences Institute, University of Southern California, 4676 Admiralty Way, Ste. 1001, Marina del Rey, CA 90292, USA"],"raw_orcid":"https://orcid.org/0000-0001-5988-8305","affiliations":[{"raw_affiliation_string":"Information Sciences Institute, University of Southern California, 4676 Admiralty Way, Ste. 1001, Marina del Rey, CA 90292, USA","institution_ids":["https://openalex.org/I1174212"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5074197492"],"corresponding_institution_ids":["https://openalex.org/I1174212"],"apc_list":{"value":1600,"currency":"CHF","value_usd":1782},"apc_paid":{"value":1600,"currency":"CHF","value_usd":1782},"fwci":0.4748,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.64477391,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":"12","issue":"3","first_page":"134","last_page":"134"},"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/T10028","display_name":"Topic Modeling","score":0.9876000285148621,"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/T10215","display_name":"Semantic Web and Ontologies","score":0.9854000210762024,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8017619848251343},{"id":"https://openalex.org/keywords/blocking","display_name":"Blocking (statistics)","score":0.7309863567352295},{"id":"https://openalex.org/keywords/schema","display_name":"Schema (genetic algorithms)","score":0.5645967125892639},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.5637896060943604},{"id":"https://openalex.org/keywords/unsupervised-learning","display_name":"Unsupervised learning","score":0.5102648735046387},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4627736806869507},{"id":"https://openalex.org/keywords/workflow","display_name":"Workflow","score":0.4558486044406891},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4117297828197479},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3589918613433838},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.34304574131965637},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.13626861572265625}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8017619848251343},{"id":"https://openalex.org/C144745244","wikidata":"https://www.wikidata.org/wiki/Q4927286","display_name":"Blocking (statistics)","level":2,"score":0.7309863567352295},{"id":"https://openalex.org/C52146309","wikidata":"https://www.wikidata.org/wiki/Q7431116","display_name":"Schema (genetic algorithms)","level":2,"score":0.5645967125892639},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.5637896060943604},{"id":"https://openalex.org/C8038995","wikidata":"https://www.wikidata.org/wiki/Q1152135","display_name":"Unsupervised learning","level":2,"score":0.5102648735046387},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4627736806869507},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.4558486044406891},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4117297828197479},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3589918613433838},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.34304574131965637},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.13626861572265625},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.3390/info12030134","is_oa":true,"landing_page_url":"https://doi.org/10.3390/info12030134","pdf_url":"https://www.mdpi.com/2078-2489/12/3/134/pdf?version=1616148415","source":{"id":"https://openalex.org/S4210219776","display_name":"Information","issn_l":"2078-2489","issn":["2078-2489"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Information","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:9c699662b0c645e6ace92264b7851718","is_oa":true,"landing_page_url":"https://doaj.org/article/9c699662b0c645e6ace92264b7851718","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","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":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Information, Vol 12, Iss 3, p 134 (2021)","raw_type":"article"},{"id":"pmh:oai:mdpi.com:/2078-2489/12/3/134/","is_oa":true,"landing_page_url":"https://dx.doi.org/10.3390/info12030134","pdf_url":null,"source":{"id":"https://openalex.org/S4306400947","display_name":"MDPI (MDPI AG)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210097602","host_organization_name":"Multidisciplinary Digital Publishing Institute (Switzerland)","host_organization_lineage":["https://openalex.org/I4210097602"],"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":"Information; Volume 12; Issue 3; Pages: 134","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.3390/info12030134","is_oa":true,"landing_page_url":"https://doi.org/10.3390/info12030134","pdf_url":"https://www.mdpi.com/2078-2489/12/3/134/pdf?version=1616148415","source":{"id":"https://openalex.org/S4210219776","display_name":"Information","issn_l":"2078-2489","issn":["2078-2489"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Information","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.550000011920929,"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/W3137713953.pdf","grobid_xml":"https://content.openalex.org/works/W3137713953.grobid-xml"},"referenced_works_count":74,"referenced_works":["https://openalex.org/W20290297","https://openalex.org/W1124123724","https://openalex.org/W1491268609","https://openalex.org/W1504263697","https://openalex.org/W1540269031","https://openalex.org/W1547612978","https://openalex.org/W1563309267","https://openalex.org/W1679882079","https://openalex.org/W1874327257","https://openalex.org/W1910093137","https://openalex.org/W1985558865","https://openalex.org/W1987544386","https://openalex.org/W2003159902","https://openalex.org/W2013970953","https://openalex.org/W2015191210","https://openalex.org/W2024505010","https://openalex.org/W2024770506","https://openalex.org/W2031250218","https://openalex.org/W2056099064","https://openalex.org/W2058733945","https://openalex.org/W2059139185","https://openalex.org/W2091449360","https://openalex.org/W2108991785","https://openalex.org/W2109042986","https://openalex.org/W2109834209","https://openalex.org/W2111116800","https://openalex.org/W2122604280","https://openalex.org/W2123561513","https://openalex.org/W2130094385","https://openalex.org/W2132366653","https://openalex.org/W2145908616","https://openalex.org/W2157054705","https://openalex.org/W2162006472","https://openalex.org/W2199337656","https://openalex.org/W2293224202","https://openalex.org/W2407862915","https://openalex.org/W2511344297","https://openalex.org/W2521135474","https://openalex.org/W2745367645","https://openalex.org/W2759136286","https://openalex.org/W2763768291","https://openalex.org/W2799937793","https://openalex.org/W2810354439","https://openalex.org/W2918428907","https://openalex.org/W2919325267","https://openalex.org/W2950719250","https://openalex.org/W2961460076","https://openalex.org/W2964221236","https://openalex.org/W2990816204","https://openalex.org/W2995343792","https://openalex.org/W3008440336","https://openalex.org/W3008820815","https://openalex.org/W3014295153","https://openalex.org/W3030163527","https://openalex.org/W3093517588","https://openalex.org/W3094027303","https://openalex.org/W3101157305","https://openalex.org/W3102245839","https://openalex.org/W3146259567","https://openalex.org/W3169483174","https://openalex.org/W4210956590","https://openalex.org/W4242744113","https://openalex.org/W4252157188","https://openalex.org/W4254788633","https://openalex.org/W6601147126","https://openalex.org/W6632038546","https://openalex.org/W6654155348","https://openalex.org/W6656333955","https://openalex.org/W6665389842","https://openalex.org/W6678151832","https://openalex.org/W6697164496","https://openalex.org/W6713833498","https://openalex.org/W6834696944","https://openalex.org/W7075681456"],"related_works":["https://openalex.org/W2392835431","https://openalex.org/W1981780420","https://openalex.org/W2126932387","https://openalex.org/W2182707996","https://openalex.org/W1965371215","https://openalex.org/W45233828","https://openalex.org/W2964988449","https://openalex.org/W2353762239","https://openalex.org/W2397952901","https://openalex.org/W2029380707"],"abstract_inverted_index":{"Entity":[0],"Resolution":[1],"(ER)":[2],"is":[3,18,48,92,159],"the":[4,38,60,148],"problem":[5],"of":[6,56,81],"identifying":[7],"co-referent":[8],"entity":[9],"pairs":[10,55],"across":[11],"datasets,":[12,106],"including":[13],"knowledge":[14],"graphs":[15],"(KGs).":[16],"ER":[17],"an":[19,89,119],"important":[20],"prerequisite":[21],"in":[22,88,111],"many":[23],"applied":[24],"KG":[25],"search":[26],"and":[27,70,96,113,155,163],"analytics":[28],"pipelines,":[29],"with":[30,77,161],"a":[31,78,85,93,143],"typical":[32],"workflow":[33],"comprising":[34],"two":[35],"steps.":[36],"In":[37],"first":[39],"\u2019blocking\u2019":[40],"step,":[41],"entities":[42,65],"are":[43,68,109],"mapped":[44],"to":[45],"blocks.":[46],"Blocking":[47],"necessary":[49],"for":[50,73,103,123],"preempting":[51],"comparing":[52],"all":[53],"possible":[54],"entities,":[57],"as":[58,108,133,135],"(in":[59],"second":[61],"\u2018similarity\u2019":[62],"step)":[63],"only":[64],"within":[66],"blocks":[67],"paired":[69],"compared,":[71],"allowing":[72],"significant":[74],"computational":[75],"savings":[76],"minimal":[79],"loss":[80],"performance.":[82],"Unfortunately,":[83],"learning":[84,124],"blocking":[86,129],"scheme":[87],"unsupervised":[90,120],"fashion":[91],"non-trivial":[94],"problem,":[95],"it":[97,158],"has":[98],"not":[99,141],"been":[100],"properly":[101],"explored":[102],"heterogeneous,":[104],"semi-structured":[105],"such":[107],"prevalent":[110],"industrial":[112],"Web":[114],"applications.":[115],"This":[116],"article":[117],"presents":[118],"algorithmic":[121],"pipeline":[122],"Disjunctive":[125],"Normal":[126],"Form":[127],"(DNF)":[128],"schemes":[130],"on":[131,150],"KGs,":[132],"well":[134],"structurally":[136],"heterogeneous":[137],"tables":[138],"that":[139,157],"may":[140],"share":[142],"common":[144],"schema.":[145],"We":[146],"evaluate":[147],"approach":[149],"six":[151],"real-world":[152],"dataset":[153],"pairs,":[154],"show":[156],"competitive":[160],"supervised":[162],"semi-supervised":[164],"baselines.":[165]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":2}],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2025-10-10T00:00:00"}