{"id":"https://openalex.org/W4313491951","doi":"https://doi.org/10.1145/3570991.3571043","title":"Surface Name Errors in Wikipedia","display_name":"Surface Name Errors in Wikipedia","publication_year":2023,"publication_date":"2023-01-04","ids":{"openalex":"https://openalex.org/W4313491951","doi":"https://doi.org/10.1145/3570991.3571043"},"language":"en","primary_location":{"id":"doi:10.1145/3570991.3571043","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3570991.3571043","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 6th Joint International Conference on Data Science &amp; Management of Data (10th ACM IKDD CODS and 28th COMAD)","raw_type":"proceedings-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/A5056423590","display_name":"Anuj Khare","orcid":"https://orcid.org/0000-0001-6318-8002"},"institutions":[{"id":"https://openalex.org/I1317621060","display_name":"Indian Institute of Technology Guwahati","ror":"https://ror.org/0022nd079","country_code":"IN","type":"education","lineage":["https://openalex.org/I1317621060"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Anuj Khare","raw_affiliation_strings":["Indian Institute of Technology Guwahati, India"],"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology Guwahati, India","institution_ids":["https://openalex.org/I1317621060"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5000346770","display_name":"Amit Awekar","orcid":"https://orcid.org/0000-0003-1559-8247"},"institutions":[{"id":"https://openalex.org/I1317621060","display_name":"Indian Institute of Technology Guwahati","ror":"https://ror.org/0022nd079","country_code":"IN","type":"education","lineage":["https://openalex.org/I1317621060"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Amit Awekar","raw_affiliation_strings":["Indian Institute of Technology Guwahati, India"],"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology Guwahati, India","institution_ids":["https://openalex.org/I1317621060"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5056423590"],"corresponding_institution_ids":["https://openalex.org/I1317621060"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.00554818,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"123","last_page":"127"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12478","display_name":"Wikis in Education and Collaboration","score":0.9994000196456909,"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"}},"topics":[{"id":"https://openalex.org/T12478","display_name":"Wikis in Education and Collaboration","score":0.9994000196456909,"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"}},{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9983000159263611,"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":0.9966999888420105,"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":0.7867506742477417},{"id":"https://openalex.org/keywords/intuition","display_name":"Intuition","score":0.5954629182815552},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5408710837364197},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.48440104722976685},{"id":"https://openalex.org/keywords/encyclopedia","display_name":"Encyclopedia","score":0.457609623670578},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.45018211007118225},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.34300339221954346},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.33423835039138794}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7867506742477417},{"id":"https://openalex.org/C132010649","wikidata":"https://www.wikidata.org/wiki/Q189222","display_name":"Intuition","level":2,"score":0.5954629182815552},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5408710837364197},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.48440104722976685},{"id":"https://openalex.org/C148863701","wikidata":"https://www.wikidata.org/wiki/Q5292","display_name":"Encyclopedia","level":2,"score":0.457609623670578},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.45018211007118225},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.34300339221954346},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33423835039138794},{"id":"https://openalex.org/C161191863","wikidata":"https://www.wikidata.org/wiki/Q199655","display_name":"Library science","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3570991.3571043","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3570991.3571043","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 6th Joint International Conference on Data Science &amp; Management of Data (10th ACM IKDD CODS and 28th COMAD)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.6399999856948853}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W1964189668","https://openalex.org/W2120845601","https://openalex.org/W2146314642","https://openalex.org/W2538279803","https://openalex.org/W2892181857","https://openalex.org/W3197398192","https://openalex.org/W3204085121","https://openalex.org/W4220792295"],"related_works":["https://openalex.org/W2348562996","https://openalex.org/W4387776128","https://openalex.org/W3010321750","https://openalex.org/W4394774294","https://openalex.org/W3159833212","https://openalex.org/W4244686159","https://openalex.org/W3011873497","https://openalex.org/W3007654203","https://openalex.org/W2186132238","https://openalex.org/W2201477785"],"abstract_inverted_index":{"Surface":[0],"name":[1,29,39,98,134,156,193,212],"is":[2,45,52,59,90,105],"the":[3,138,173,188],"string":[4],"used":[5,60],"to":[6,8,127,186],"refer":[7],"an":[9],"entity":[10],"in":[11,41,119,130,143],"a":[12,53,75,150,200],"text":[13],"corpus.":[14],"Crowd-sourced":[15],"knowledge":[16,55],"repositories":[17],"such":[18,84],"as":[19,74,85],"Wikipedia":[20,51,73,118,131,160,166,185],"can":[21,206],"have":[22,132,198],"multiple":[23],"types":[24],"of":[25,63,102,140,153,172,184,190],"errors,":[26],"including":[27],"surface":[28,38,97,108,133,155,192,211],"errors.":[30,99,135],"This":[31,43],"paper":[32],"focuses":[33],"on":[34,162],"identifying":[35],"and":[36,57,158],"correcting":[37],"errors":[40,157],"Wikipedia.":[42],"problem":[44],"important":[46],"for":[47],"two":[48,182],"reasons.":[49],"First,":[50,146],"popular":[54],"repository,":[56],"it":[58],"by":[61,176],"millions":[62],"people":[64,205],"every":[65],"day.":[66],"Second,":[67,179],"many":[68,81],"machine":[69],"learning":[70],"models":[71],"use":[72],"training":[76],"dataset.":[77],"Existing":[78],"work":[79,93,104,142],"addresses":[80],"related":[82],"problems":[83],"Entity":[86],"Linking.":[87],"However,":[88],"there":[89],"no":[91],"direct":[92],"that":[94,106,124],"deals":[95],"with":[96],"The":[100,165],"intuition":[101],"our":[103,141,163,177,191,210],"infrequent":[107],"names":[109],"are":[110],"typically":[111],"wrong.":[112],"Using":[113],"this":[114],"heuristic,":[115],"we":[116,147,180,197],"analyze":[117,149],"eight":[120],"languages.":[121],"We":[122,136],"observe":[123],"about":[125,209],"3":[126],"6%":[128],"mentions":[129],"verify":[137],"quality":[139,189],"three":[144],"ways.":[145],"manually":[148],"small":[151],"sample":[152],"predicted":[154],"update":[159],"based":[161],"predictions.":[164,214],"community":[167],"accepted":[168],"more":[169],"than":[170],"99%":[171],"corrections":[174],"suggested":[175],"work.":[178],"compare":[181],"snapshots":[183],"estimate":[187],"error":[194,213],"prediction.":[195],"Third,":[196],"built":[199],"web-based":[201],"feedback":[202,208],"portal":[203],"where":[204],"give":[207]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
