{"id":"https://openalex.org/W3000512475","doi":"https://doi.org/10.14778/3372716.3372727","title":"Mining an \"anti-knowledge base\" from Wikipedia updates with applications to fact checking and beyond","display_name":"Mining an \"anti-knowledge base\" from Wikipedia updates with applications to fact checking and beyond","publication_year":2019,"publication_date":"2019-12-09","ids":{"openalex":"https://openalex.org/W3000512475","doi":"https://doi.org/10.14778/3372716.3372727","mag":"3000512475"},"language":"en","primary_location":{"id":"doi:10.14778/3372716.3372727","is_oa":false,"landing_page_url":"https://doi.org/10.14778/3372716.3372727","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":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5030307010","display_name":"Georgios Karagiannis","orcid":"https://orcid.org/0000-0002-2677-1474"},"institutions":[{"id":"https://openalex.org/I205783295","display_name":"Cornell University","ror":"https://ror.org/05bnh6r87","country_code":"US","type":"education","lineage":["https://openalex.org/I205783295"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Georgios Karagiannis","raw_affiliation_strings":["Cornell University"],"affiliations":[{"raw_affiliation_string":"Cornell University","institution_ids":["https://openalex.org/I205783295"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087259526","display_name":"Immanuel Trummer","orcid":"https://orcid.org/0000-0002-7203-2349"},"institutions":[{"id":"https://openalex.org/I205783295","display_name":"Cornell University","ror":"https://ror.org/05bnh6r87","country_code":"US","type":"education","lineage":["https://openalex.org/I205783295"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Immanuel Trummer","raw_affiliation_strings":["Cornell University"],"affiliations":[{"raw_affiliation_string":"Cornell University","institution_ids":["https://openalex.org/I205783295"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102329375","display_name":"Saehan Jo","orcid":null},"institutions":[{"id":"https://openalex.org/I205783295","display_name":"Cornell University","ror":"https://ror.org/05bnh6r87","country_code":"US","type":"education","lineage":["https://openalex.org/I205783295"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Saehan Jo","raw_affiliation_strings":["Cornell University"],"affiliations":[{"raw_affiliation_string":"Cornell University","institution_ids":["https://openalex.org/I205783295"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012586106","display_name":"Shubham Khandelwal","orcid":"https://orcid.org/0000-0003-3165-1140"},"institutions":[{"id":"https://openalex.org/I205783295","display_name":"Cornell University","ror":"https://ror.org/05bnh6r87","country_code":"US","type":"education","lineage":["https://openalex.org/I205783295"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shubham Khandelwal","raw_affiliation_strings":["Cornell University"],"affiliations":[{"raw_affiliation_string":"Cornell University","institution_ids":["https://openalex.org/I205783295"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024842018","display_name":"Xuezhi Wang","orcid":"https://orcid.org/0000-0001-7592-2358"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xuezhi Wang","raw_affiliation_strings":["Google"],"affiliations":[{"raw_affiliation_string":"Google","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043275971","display_name":"Cong Yu","orcid":"https://orcid.org/0000-0001-7331-2345"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Cong Yu","raw_affiliation_strings":["Google"],"affiliations":[{"raw_affiliation_string":"Google","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5030307010"],"corresponding_institution_ids":["https://openalex.org/I205783295"],"apc_list":null,"apc_paid":null,"fwci":1.9602,"has_fulltext":false,"cited_by_count":20,"citation_normalized_percentile":{"value":0.89981432,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":"13","issue":"4","first_page":"561","last_page":"573"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9945999979972839,"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"}},"topics":[{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9945999979972839,"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/T10028","display_name":"Topic Modeling","score":0.9936000108718872,"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/T12478","display_name":"Wikis in Education and Collaboration","score":0.9837999939918518,"subfield":{"id":"https://openalex.org/subfields/3315","display_name":"Communication"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8590419888496399},{"id":"https://openalex.org/keywords/heuristics","display_name":"Heuristics","score":0.7183943390846252},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5232947468757629},{"id":"https://openalex.org/keywords/knowledge-base","display_name":"Knowledge base","score":0.5119277238845825},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5016069412231445},{"id":"https://openalex.org/keywords/benchmarking","display_name":"Benchmarking","score":0.48209479451179504},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.4700915813446045},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.44486644864082336},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.42623552680015564},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.34684112668037415},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.26065918803215027}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8590419888496399},{"id":"https://openalex.org/C127705205","wikidata":"https://www.wikidata.org/wiki/Q5748245","display_name":"Heuristics","level":2,"score":0.7183943390846252},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5232947468757629},{"id":"https://openalex.org/C4554734","wikidata":"https://www.wikidata.org/wiki/Q593744","display_name":"Knowledge base","level":2,"score":0.5119277238845825},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5016069412231445},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.48209479451179504},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.4700915813446045},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.44486644864082336},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.42623552680015564},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.34684112668037415},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.26065918803215027},{"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/C162853370","wikidata":"https://www.wikidata.org/wiki/Q39809","display_name":"Marketing","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},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.14778/3372716.3372727","is_oa":false,"landing_page_url":"https://doi.org/10.14778/3372716.3372727","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"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W9014458","https://openalex.org/W790941020","https://openalex.org/W2000519162","https://openalex.org/W2086413055","https://openalex.org/W2115461474","https://openalex.org/W2118388899","https://openalex.org/W2129629757","https://openalex.org/W2134305421","https://openalex.org/W2144416276","https://openalex.org/W2155160033","https://openalex.org/W2167187514","https://openalex.org/W2167571757","https://openalex.org/W2185970506","https://openalex.org/W2251913848","https://openalex.org/W2408493841","https://openalex.org/W2524497217","https://openalex.org/W2585226541","https://openalex.org/W2591700809","https://openalex.org/W2604700701","https://openalex.org/W2743800013","https://openalex.org/W2758097047","https://openalex.org/W2769041395","https://openalex.org/W2792939464","https://openalex.org/W2799228294","https://openalex.org/W2913970915","https://openalex.org/W2936597270","https://openalex.org/W2952288398","https://openalex.org/W2963341956","https://openalex.org/W3179923213","https://openalex.org/W6679959949","https://openalex.org/W6754006147","https://openalex.org/W6759106391"],"related_works":["https://openalex.org/W4238897586","https://openalex.org/W435179959","https://openalex.org/W2619091065","https://openalex.org/W2059640416","https://openalex.org/W1490753184","https://openalex.org/W2284465472","https://openalex.org/W2291782699","https://openalex.org/W1993948687","https://openalex.org/W2011676020","https://openalex.org/W2329895846"],"abstract_inverted_index":{"We":[0,71,105,203,225],"introduce":[1],"the":[2,31,53,94,102,132,146,160,190,200,229,238],"problem":[3],"of":[4,34,46,56,93,97,101,148,162,187,196],"anti-knowledge":[5,107],"mining.":[6],"Our":[7,172],"goal":[8],"is":[9,99,175],"to":[10,68,140,169,216,234],"create":[11],"an":[12,76,151],"\"anti-knowledge":[13],"base\"":[14],"that":[15,82,205,228],"contains":[16],"factual":[17,57,84],"mistakes.":[18,85,224],"The":[19],"resulting":[20],"data":[21,39,177,215],"can":[22,231],"be":[23,232],"used":[24,233],"for":[25],"analysis,":[26],"training,":[27],"and":[28,165,193],"benchmarking":[29],"in":[30,159,189,199],"research":[32],"domain":[33],"automated":[35],"fact":[36,44],"checking.":[37],"Prior":[38],"sets":[40],"feature":[41],"manually":[42],"generated":[43],"checks":[45],"famous":[47],"misclaims.":[48],"Instead,":[49],"we":[50,113,123,144,156,212],"focus":[51],"on":[52,131,220,237],"long":[54],"tail":[55],"mistakes":[58,73,158,183,236],"made":[59,130],"by":[60,75,108],"Web":[61],"authors,":[62],"ranging":[63],"from":[64,79],"erroneous":[65],"sports":[66],"results":[67],"incorrect":[69],"capitals.":[70],"mine":[72,106],"automatically,":[74],"unsupervised":[77],"approach,":[78],"Wikipedia":[80,125],"updates":[81,88,117,126],"correct":[83],"Identifying":[86],"such":[87],"(only":[89],"a":[90,109,141,176,185,194],"small":[91],"fraction":[92],"total":[95],"number":[96],"updates)":[98],"one":[100],"primary":[103],"challenges.":[104],"multi-step":[110],"pipeline.":[111],"First,":[112],"filter":[114],"out":[115],"candidate":[116],"via":[118,150],"several":[119,170,218],"simple":[120],"heuristics.":[121],"Next,":[122],"correlate":[124],"with":[127,184],"other":[128],"statements":[129],"Web.":[133,240],"Using":[134],"claim":[135],"occurrence":[136],"frequencies":[137],"as":[138],"input":[139],"probabilistic":[142],"model,":[143],"infer":[145],"likelihood":[147],"corrections":[149],"iterative":[152],"expectation-maximization":[153],"approach.":[154],"Finally,":[155],"extract":[157],"form":[161],"subject-predicate-object":[163],"triples":[164],"rank":[166],"them":[167],"according":[168],"criteria.":[171],"end":[173],"result":[174],"set":[178],"containing":[179],"over":[180,197],"110,000":[181],"ranked":[182],"precision":[186,195],"85%":[188],"top":[191,201],"1%":[192],"60%":[198],"25%.":[202],"demonstrate":[204],"baselines":[206],"achieve":[207],"significantly":[208],"lower":[209],"precision.":[210],"Also,":[211],"exploit":[213],"our":[214],"verify":[217],"hypothesis":[219],"why":[221],"users":[222],"make":[223],"finally":[226],"show":[227],"AKB":[230],"find":[235],"entire":[239]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}