{"id":"https://openalex.org/W2035168844","doi":"https://doi.org/10.1145/2791347.2791353","title":"Top-k entity augmentation using consistent set covering","display_name":"Top-k entity augmentation using consistent set covering","publication_year":2015,"publication_date":"2015-06-29","ids":{"openalex":"https://openalex.org/W2035168844","doi":"https://doi.org/10.1145/2791347.2791353","mag":"2035168844"},"language":"en","primary_location":{"id":"doi:10.1145/2791347.2791353","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2791347.2791353","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 27th International Conference on Scientific and Statistical Database Management","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://tud.qucosa.de/id/qucosa%3A80667","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5031718315","display_name":"Julian Eberius","orcid":null},"institutions":[{"id":"https://openalex.org/I78650965","display_name":"TU Dresden","ror":"https://ror.org/042aqky30","country_code":"DE","type":"education","lineage":["https://openalex.org/I78650965"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Julian Eberius","raw_affiliation_strings":["Technische Universit\u00e4t Dresden","[Technische Universitat, Dresden]"],"affiliations":[{"raw_affiliation_string":"Technische Universit\u00e4t Dresden","institution_ids":["https://openalex.org/I78650965"]},{"raw_affiliation_string":"[Technische Universitat, Dresden]","institution_ids":["https://openalex.org/I78650965"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000229374","display_name":"Maik Thiele","orcid":"https://orcid.org/0000-0002-1665-977X"},"institutions":[{"id":"https://openalex.org/I78650965","display_name":"TU Dresden","ror":"https://ror.org/042aqky30","country_code":"DE","type":"education","lineage":["https://openalex.org/I78650965"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Maik Thiele","raw_affiliation_strings":["Technische Universit\u00e4t Dresden","[Technische Universitat, Dresden]"],"affiliations":[{"raw_affiliation_string":"Technische Universit\u00e4t Dresden","institution_ids":["https://openalex.org/I78650965"]},{"raw_affiliation_string":"[Technische Universitat, Dresden]","institution_ids":["https://openalex.org/I78650965"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055054068","display_name":"Katrin Braunschweig","orcid":null},"institutions":[{"id":"https://openalex.org/I78650965","display_name":"TU Dresden","ror":"https://ror.org/042aqky30","country_code":"DE","type":"education","lineage":["https://openalex.org/I78650965"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Katrin Braunschweig","raw_affiliation_strings":["Technische Universit\u00e4t Dresden","[Technische Universitat, Dresden]"],"affiliations":[{"raw_affiliation_string":"Technische Universit\u00e4t Dresden","institution_ids":["https://openalex.org/I78650965"]},{"raw_affiliation_string":"[Technische Universitat, Dresden]","institution_ids":["https://openalex.org/I78650965"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5063512642","display_name":"Wolfgang Lehner","orcid":"https://orcid.org/0000-0001-8107-2775"},"institutions":[{"id":"https://openalex.org/I78650965","display_name":"TU Dresden","ror":"https://ror.org/042aqky30","country_code":"DE","type":"education","lineage":["https://openalex.org/I78650965"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Wolfgang Lehner","raw_affiliation_strings":["Technische Universit\u00e4t Dresden","[Technische Universitat, Dresden]"],"affiliations":[{"raw_affiliation_string":"Technische Universit\u00e4t Dresden","institution_ids":["https://openalex.org/I78650965"]},{"raw_affiliation_string":"[Technische Universitat, Dresden]","institution_ids":["https://openalex.org/I78650965"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5031718315"],"corresponding_institution_ids":["https://openalex.org/I78650965"],"apc_list":null,"apc_paid":null,"fwci":4.9492,"has_fulltext":false,"cited_by_count":30,"citation_normalized_percentile":{"value":0.94931217,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"12"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9976999759674072,"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":0.9952999949455261,"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":0.8707214593887329},{"id":"https://openalex.org/keywords/schema-matching","display_name":"Schema matching","score":0.7749192714691162},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6295533180236816},{"id":"https://openalex.org/keywords/schema","display_name":"Schema (genetic algorithms)","score":0.5731199383735657},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5598287582397461},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5501941442489624},{"id":"https://openalex.org/keywords/table","display_name":"Table (database)","score":0.5138962268829346},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.4935365915298462},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.48791858553886414},{"id":"https://openalex.org/keywords/data-integration","display_name":"Data integration","score":0.29881399869918823},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.21939480304718018},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.09842988848686218}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8707214593887329},{"id":"https://openalex.org/C2777327318","wikidata":"https://www.wikidata.org/wiki/Q1408390","display_name":"Schema matching","level":3,"score":0.7749192714691162},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6295533180236816},{"id":"https://openalex.org/C52146309","wikidata":"https://www.wikidata.org/wiki/Q7431116","display_name":"Schema (genetic algorithms)","level":2,"score":0.5731199383735657},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5598287582397461},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5501941442489624},{"id":"https://openalex.org/C45235069","wikidata":"https://www.wikidata.org/wiki/Q278425","display_name":"Table (database)","level":2,"score":0.5138962268829346},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.4935365915298462},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.48791858553886414},{"id":"https://openalex.org/C72634772","wikidata":"https://www.wikidata.org/wiki/Q386824","display_name":"Data integration","level":2,"score":0.29881399869918823},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.21939480304718018},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.09842988848686218},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/2791347.2791353","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2791347.2791353","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 27th International Conference on Scientific and Statistical Database Management","raw_type":"proceedings-article"},{"id":"pmh:oai:qucosa:de:qucosa:80667","is_oa":true,"landing_page_url":"https://tud.qucosa.de/id/qucosa%3A80667","pdf_url":null,"source":{"id":"https://openalex.org/S4377196312","display_name":"Qucosa (Saxon State and University Library Dresden)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I3132420320","host_organization_name":"SLUB Dresden","host_organization_lineage":["https://openalex.org/I3132420320"],"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":null,"raw_type":"doc-type:Text"}],"best_oa_location":{"id":"pmh:oai:qucosa:de:qucosa:80667","is_oa":true,"landing_page_url":"https://tud.qucosa.de/id/qucosa%3A80667","pdf_url":null,"source":{"id":"https://openalex.org/S4377196312","display_name":"Qucosa (Saxon State and University Library Dresden)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I3132420320","host_organization_name":"SLUB Dresden","host_organization_lineage":["https://openalex.org/I3132420320"],"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":null,"raw_type":"doc-type:Text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W1521736627","https://openalex.org/W1969621019","https://openalex.org/W1996505782","https://openalex.org/W2005324184","https://openalex.org/W2008896880","https://openalex.org/W2016207616","https://openalex.org/W2016929496","https://openalex.org/W2029891043","https://openalex.org/W2066806792","https://openalex.org/W2092364718","https://openalex.org/W2099799055","https://openalex.org/W2104042955","https://openalex.org/W2108223890","https://openalex.org/W2111869785","https://openalex.org/W2140116426","https://openalex.org/W2251214202","https://openalex.org/W2295240344"],"related_works":["https://openalex.org/W2471940468","https://openalex.org/W4226075635","https://openalex.org/W3130973930","https://openalex.org/W2047599596","https://openalex.org/W2372910313","https://openalex.org/W1528218860","https://openalex.org/W2406112091","https://openalex.org/W2125859764","https://openalex.org/W2029826694","https://openalex.org/W2159303222"],"abstract_inverted_index":{"Entity":[0],"augmentation":[1,212],"is":[2,46,90],"a":[3,9,14,24,37,49,78,93,112,160,163,181,189],"query":[4,233],"type":[5],"in":[6,111,115,196],"which,":[7],"given":[8],"set":[10,52,153,219],"of":[11,17,23,32,53,63,96,134,150,210,224],"entities":[12],"and":[13,69,138,146,155,162,188,193,208,228],"large":[15,51,61,94],"corpus":[16,184],"possible":[18],"data":[19,54,136],"sources,":[20],"the":[21,33,82,88,117,126,132,135,148,206,211],"values":[22],"missing":[25],"attribute":[26],"are":[27,200],"to":[28,41,101,107,130,172],"be":[29,215],"retrieved.":[30],"State":[31],"art":[34],"methods":[35,73,139],"return":[36,77],"single":[38,79],"result":[39,80,89],"that,":[40],"cover":[42],"all":[43],"queried":[44],"entities,":[45],"fused":[47],"from":[48,92,124],"potentially":[50],"sources.":[55],"We":[56,104,167],"argue":[57],"that":[58,81,98,205],"queries":[59,110],"on":[60,159],"corpora":[62],"heterogeneous":[64],"sources":[65,97,137],"using":[66,217],"information":[67],"retrieval":[68,192],"automatic":[70],"schema":[71],"matching":[72,194],"can":[74,84,128,214],"not":[75],"easily":[76],"user":[83,99,127],"trust,":[85],"especially":[86],"if":[87],"composed":[91],"number":[95],"has":[100],"verify":[102],"manually.":[103],"therefore":[105],"propose":[106],"process":[108],"these":[109,170,198],"Top-k":[113],"fashion,":[114],"which":[116,125,197],"system":[118,195],"produces":[119],"multiple":[120,231],"minimal":[121],"consistent":[122],"solutions":[123],"choose":[129],"resolve":[131],"uncertainty":[133],"used.":[140],"In":[141],"this":[142],"paper,":[143],"we":[144],"introduce":[145],"formalize":[147],"problem":[149],"consistent,":[151],"multi-solution":[152],"covering,":[154],"present":[156],"algorithms":[157,171,199],"based":[158],"greedy":[161],"genetic":[164],"optimization":[165],"approach.":[166],"then":[168],"apply":[169],"Web":[173,182,190],"table-based":[174],"entity":[175],"augmentation.":[176],"The":[177],"publication":[178],"further":[179],"includes":[180],"table":[183,191],"with":[185],"100M":[186],"tables,":[187],"implemented.":[201],"Our":[202],"experiments":[203],"show":[204],"consistency":[207],"minimality":[209],"results":[213],"improved":[216],"our":[218],"covering":[220],"approach,":[221],"without":[222],"loss":[223],"precision":[225],"or":[226],"coverage":[227],"while":[229],"producing":[230],"alternative":[232],"results.":[234]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":4}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}