{"id":"https://openalex.org/W3004185181","doi":"https://doi.org/10.1145/3366423.3380205","title":"Novel Entity Discovery from Web Tables","display_name":"Novel Entity Discovery from Web Tables","publication_year":2020,"publication_date":"2020-04-20","ids":{"openalex":"https://openalex.org/W3004185181","doi":"https://doi.org/10.1145/3366423.3380205","mag":"3004185181"},"language":"en","primary_location":{"id":"doi:10.1145/3366423.3380205","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3366423.3380205","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of The Web Conference 2020","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3366423.3380205","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Shuo Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I1299907687","display_name":"Bloomberg (United States)","ror":"https://ror.org/02rdpzb15","country_code":"US","type":"company","lineage":["https://openalex.org/I1299907687"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shuo Zhang","raw_affiliation_strings":["Bloomberg"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Bloomberg","institution_ids":["https://openalex.org/I1299907687"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Edgar Meij","orcid":null},"institutions":[{"id":"https://openalex.org/I1299907687","display_name":"Bloomberg (United States)","ror":"https://ror.org/02rdpzb15","country_code":"US","type":"company","lineage":["https://openalex.org/I1299907687"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Edgar Meij","raw_affiliation_strings":["Bloomberg"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Bloomberg","institution_ids":["https://openalex.org/I1299907687"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Krisztian Balog","orcid":null},"institutions":[{"id":"https://openalex.org/I92008406","display_name":"University of Stavanger","ror":"https://ror.org/02qte9q33","country_code":"NO","type":"education","lineage":["https://openalex.org/I92008406"]}],"countries":["NO"],"is_corresponding":false,"raw_author_name":"Krisztian Balog","raw_affiliation_strings":["University of Stavanger"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Stavanger","institution_ids":["https://openalex.org/I92008406"]}]},{"author_position":"last","author":{"id":null,"display_name":"Ridho Reinanda","orcid":null},"institutions":[{"id":"https://openalex.org/I1299907687","display_name":"Bloomberg (United States)","ror":"https://ror.org/02rdpzb15","country_code":"US","type":"company","lineage":["https://openalex.org/I1299907687"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ridho Reinanda","raw_affiliation_strings":["Bloomberg"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Bloomberg","institution_ids":["https://openalex.org/I1299907687"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":28,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1298","last_page":"1308"},"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9851999878883362,"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"}},{"id":"https://openalex.org/T10215","display_name":"Semantic Web and Ontologies","score":0.9811999797821045,"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/leverage","display_name":"Leverage (statistics)","score":0.5860999822616577},{"id":"https://openalex.org/keywords/table","display_name":"Table (database)","score":0.5759999752044678},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5343999862670898},{"id":"https://openalex.org/keywords/sort","display_name":"sort","score":0.4620000123977661},{"id":"https://openalex.org/keywords/entity-linking","display_name":"Entity linking","score":0.43939998745918274},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.438400000333786},{"id":"https://openalex.org/keywords/knowledge-base","display_name":"Knowledge base","score":0.41690000891685486},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.37790000438690186}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8169999718666077},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6499000191688538},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.5860999822616577},{"id":"https://openalex.org/C45235069","wikidata":"https://www.wikidata.org/wiki/Q278425","display_name":"Table (database)","level":2,"score":0.5759999752044678},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5343999862670898},{"id":"https://openalex.org/C88548561","wikidata":"https://www.wikidata.org/wiki/Q347599","display_name":"sort","level":2,"score":0.4620000123977661},{"id":"https://openalex.org/C96711827","wikidata":"https://www.wikidata.org/wiki/Q17012245","display_name":"Entity linking","level":3,"score":0.43939998745918274},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.438400000333786},{"id":"https://openalex.org/C4554734","wikidata":"https://www.wikidata.org/wiki/Q593744","display_name":"Knowledge base","level":2,"score":0.41690000891685486},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.38850000500679016},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.37790000438690186},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3732999861240387},{"id":"https://openalex.org/C2779135771","wikidata":"https://www.wikidata.org/wiki/Q403574","display_name":"Named-entity recognition","level":3,"score":0.36640000343322754},{"id":"https://openalex.org/C2129575","wikidata":"https://www.wikidata.org/wiki/Q54837","display_name":"Semantic Web","level":2,"score":0.32339999079704285},{"id":"https://openalex.org/C118643609","wikidata":"https://www.wikidata.org/wiki/Q189210","display_name":"Web application","level":2,"score":0.3037000000476837},{"id":"https://openalex.org/C132964779","wikidata":"https://www.wikidata.org/wiki/Q2110223","display_name":"Raw data","level":2,"score":0.3037000000476837},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.287200003862381},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.2818000018596649},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.2809999883174896},{"id":"https://openalex.org/C2776937971","wikidata":"https://www.wikidata.org/wiki/Q4384217","display_name":"Heading (navigation)","level":2,"score":0.27379998564720154},{"id":"https://openalex.org/C120567893","wikidata":"https://www.wikidata.org/wiki/Q1582085","display_name":"Knowledge extraction","level":2,"score":0.26840001344680786},{"id":"https://openalex.org/C35578498","wikidata":"https://www.wikidata.org/wiki/Q193424","display_name":"Web service","level":2,"score":0.26750001311302185},{"id":"https://openalex.org/C68476402","wikidata":"https://www.wikidata.org/wiki/Q1456936","display_name":"Table of contents","level":2,"score":0.2630000114440918},{"id":"https://openalex.org/C42058472","wikidata":"https://www.wikidata.org/wiki/Q810214","display_name":"Base (topology)","level":2,"score":0.257099986076355},{"id":"https://openalex.org/C135598885","wikidata":"https://www.wikidata.org/wiki/Q1366302","display_name":"Row","level":2,"score":0.2540000081062317},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.25099998712539673}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3366423.3380205","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3366423.3380205","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of The Web Conference 2020","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2002.00206","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2002.00206","pdf_url":"https://arxiv.org/pdf/2002.00206","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"}],"best_oa_location":{"id":"doi:10.1145/3366423.3380205","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3366423.3380205","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of The Web Conference 2020","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W92812941","https://openalex.org/W1721994796","https://openalex.org/W2016753842","https://openalex.org/W2020022499","https://openalex.org/W2035274534","https://openalex.org/W2046441607","https://openalex.org/W2092364718","https://openalex.org/W2104042955","https://openalex.org/W2148019918","https://openalex.org/W2174529133","https://openalex.org/W2340354588","https://openalex.org/W2341748398","https://openalex.org/W2398606196","https://openalex.org/W2425367731","https://openalex.org/W2533904613","https://openalex.org/W2536015822","https://openalex.org/W2575118467","https://openalex.org/W2612773933","https://openalex.org/W2762307198","https://openalex.org/W2788550262","https://openalex.org/W2799217228","https://openalex.org/W2809365555","https://openalex.org/W2888236192","https://openalex.org/W2945802750","https://openalex.org/W2963691861","https://openalex.org/W2971470875","https://openalex.org/W3102018197"],"related_works":[],"abstract_inverted_index":{"When":[0,236],"working":[1],"with":[2,70],"any":[3],"sort":[4],"of":[5,51,133,156,204,255],"knowledge":[6],"base":[7],"(KB)":[8],"one":[9],"has":[10],"to":[11,33,68,83,102,107,120,131,172,184,193,201],"make":[12],"sure":[13],"it":[14,207],"is":[15,208],"as":[16,20,22,28,196],"complete":[17],"and":[18,37,63,88,128,141,170,188],"also":[19,159,183,229],"up-to-date":[21],"possible.":[23],"Both":[24],"tasks":[25],"are":[26,39,61],"non-trivial":[27],"they":[29,46],"require":[30,47],"recall-oriented":[31],"efforts":[32],"determine":[34,103],"which":[35,104,108],"entities":[36,169],"relationships":[38],"missing":[40],"from":[41],"the":[42,55,58,65,78,152,179,202,209,214],"KB.":[43,135],"As":[44],"such":[45,81],"a":[48,134,138,250],"significant":[49],"amount":[50],"labor.":[52],"Tables":[53],"on":[54,57,142,212],"Web":[56],"other":[59],"hand":[60],"abundant":[62],"have":[64],"distinct":[66],"potential":[67],"assist":[69],"these":[71,167],"tasks.":[72],"In":[73],"particular,":[74],"we":[75,99,112,147,243],"can":[76],"leverage":[77],"content":[79,98],"in":[80,154,178,217,253],"tables":[82,92],"discover":[84],"new":[85],"entities,":[86],"properties,":[87],"relationships.":[89,190],"Because":[90],"web":[91,218],"typically":[93],"only":[94,174,224],"contain":[95],"raw":[96],"textual":[97],"first":[100,117,210],"need":[101],"cells":[105,127,216],"refer":[106,192],"known":[109],"entities\u2014a":[110],"task":[111,118,164],"dub":[113],"table-to-KB":[114],"matching.":[115],"This":[116],"aims":[119],"infer":[121],"table":[122,126,181],"semantics":[123],"by":[124],"linking":[125],"heading":[129],"columns":[130],"elements":[132],"We":[136,191],"propose":[137],"feature-based":[139],"method":[140,221],"two":[143],"public":[144],"test":[145,241],"collections":[146],"demonstrate":[148],"substantial":[149],"improvements":[150],"over":[151,257],"state-of-the-art":[153],"terms":[155,254],"precision":[157,256],"whilst":[158,260],"improving":[160],"recall.":[161],"Then":[162],"second":[163],"builds":[165],"upon":[166],"linked":[168],"properties":[171],"not":[173,223],"identify":[175],"novel":[176,197,230],"ones":[177],"same":[180],"but":[182,228],"bootstrap":[185],"their":[186],"type":[187],"additional":[189],"this":[194],"process":[195],"entity":[198],"discovery":[199],"and,":[200],"best":[203],"our":[205,246,258],"knowledge,":[206],"endeavor":[211],"mining":[213],"unlinked":[215],"tables.":[219],"Our":[220],"identifies":[222],"out-of-KB":[225],"(\u201cnovel\u201d)":[226],"information":[227],"aliases":[231],"for":[232],"in-KB":[233],"(\u201cknown\u201d)":[234],"entities.":[235],"evaluated":[237],"using":[238],"three":[239],"purpose-built":[240],"collections,":[242],"find":[244],"that":[245],"proposed":[247],"approaches":[248],"obtain":[249],"marked":[251],"improvement":[252],"baselines":[259],"keeping":[261],"recall":[262],"stable.":[263]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":10},{"year":2020,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2020-02-07T00:00:00"}