{"id":"https://openalex.org/W2026051344","doi":"https://doi.org/10.1145/1498759.1498813","title":"Information arbitrage across multi-lingual Wikipedia","display_name":"Information arbitrage across multi-lingual Wikipedia","publication_year":2009,"publication_date":"2009-02-09","ids":{"openalex":"https://openalex.org/W2026051344","doi":"https://doi.org/10.1145/1498759.1498813","mag":"2026051344"},"language":"en","primary_location":{"id":"doi:10.1145/1498759.1498813","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1498759.1498813","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Second ACM International Conference on Web Search and Data Mining","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/A5064931337","display_name":"Eytan Adar","orcid":"https://orcid.org/0000-0003-1911-836X"},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Eytan Adar","raw_affiliation_strings":["University of Washington, Seattle, WA","University Of Washington (Seattle, WA)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Washington, Seattle, WA","institution_ids":["https://openalex.org/I201448701"]},{"raw_affiliation_string":"University Of Washington (Seattle, WA)","institution_ids":["https://openalex.org/I201448701"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103923116","display_name":"Michael Skinner","orcid":null},"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":"Michael Skinner","raw_affiliation_strings":["Google, Seattle, WA","Google, Seattle, WA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google, Seattle, WA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google, Seattle, WA#TAB#","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5085011940","display_name":"Daniel S. Weld","orcid":"https://orcid.org/0000-0002-3255-0109"},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Daniel S. Weld","raw_affiliation_strings":["University of Washington, Seattle, WA","University Of Washington (Seattle, WA)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Washington, Seattle, WA","institution_ids":["https://openalex.org/I201448701"]},{"raw_affiliation_string":"University Of Washington (Seattle, WA)","institution_ids":["https://openalex.org/I201448701"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":25.9398,"has_fulltext":false,"cited_by_count":96,"citation_normalized_percentile":{"value":0.99522217,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"94","last_page":"103"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12478","display_name":"Wikis in Education and Collaboration","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9979000091552734,"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":0.9814000129699707,"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":0.811030387878418},{"id":"https://openalex.org/keywords/scope","display_name":"Scope (computer science)","score":0.7796564102172852},{"id":"https://openalex.org/keywords/german","display_name":"German","score":0.6442605257034302},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.5418354868888855},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5058434009552002},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4748062193393707},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4713056981563568},{"id":"https://openalex.org/keywords/arbitrage","display_name":"Arbitrage","score":0.4669042229652405},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.45326942205429077},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.16800716519355774},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.12761852145195007}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.811030387878418},{"id":"https://openalex.org/C2778012447","wikidata":"https://www.wikidata.org/wiki/Q1034415","display_name":"Scope (computer science)","level":2,"score":0.7796564102172852},{"id":"https://openalex.org/C154775046","wikidata":"https://www.wikidata.org/wiki/Q188","display_name":"German","level":2,"score":0.6442605257034302},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.5418354868888855},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5058434009552002},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4748062193393707},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4713056981563568},{"id":"https://openalex.org/C160623529","wikidata":"https://www.wikidata.org/wiki/Q273088","display_name":"Arbitrage","level":2,"score":0.4669042229652405},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.45326942205429077},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.16800716519355774},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.12761852145195007},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C106159729","wikidata":"https://www.wikidata.org/wiki/Q2294553","display_name":"Financial economics","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":3,"locations":[{"id":"doi:10.1145/1498759.1498813","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1498759.1498813","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Second ACM International Conference on Web Search and Data Mining","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.143.7383","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.143.7383","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.washington.edu/homes/weld/papers/adar-wsdm09.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.169.5159","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.169.5159","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cond.org/paper_202.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.6499999761581421,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W14574270","https://openalex.org/W50119190","https://openalex.org/W254843634","https://openalex.org/W1523949738","https://openalex.org/W1565814412","https://openalex.org/W1571200267","https://openalex.org/W1577422779","https://openalex.org/W2008896880","https://openalex.org/W2024046085","https://openalex.org/W2050459408","https://openalex.org/W2071018679","https://openalex.org/W2099253769","https://openalex.org/W2124067180","https://openalex.org/W2146304342","https://openalex.org/W2152749438","https://openalex.org/W2168943018","https://openalex.org/W2606278121","https://openalex.org/W3203128311","https://openalex.org/W7048665905"],"related_works":["https://openalex.org/W2065387230","https://openalex.org/W2323937687","https://openalex.org/W648995381","https://openalex.org/W3033791384","https://openalex.org/W2141885522","https://openalex.org/W2776312268","https://openalex.org/W4246315097","https://openalex.org/W2975591548","https://openalex.org/W346029495","https://openalex.org/W2516447249"],"abstract_inverted_index":{"The":[0],"rapid":[1],"globalization":[2],"of":[3,11,28,76,142],"Wikipedia":[4,109],"is":[5],"generating":[6],"a":[7,26,73],"parallel,":[8],"multi-lingual":[9],"corpus":[10],"unprecedented":[12],"scale.":[13],"Pages":[14],"for":[15,72,107],"the":[16,53,70,87,135,140],"same":[17],"topic":[18],"in":[19,43,58,80,89,117,139],"many":[20],"different":[21,40,59],"languages":[22,60,84],"emerge":[23],"both":[24,63],"as":[25,114],"result":[27],"manual":[29],"translation":[30],"and":[31,46,65,99,120,131],"independent":[32],"development.":[33],"Unfortunately,":[34],"these":[35],"pages":[36],"may":[37],"appear":[38],"at":[39],"times,":[41],"vary":[42],"size,":[44],"scope,":[45],"quality.":[47],"Furthermore,":[48],"differential":[49],"growth":[50],"rates":[51],"cause":[52],"conceptual":[54],"mapping":[55],"between":[56,123],"articles":[57,79],"to":[61,85],"be":[62],"complex":[64],"dynamic.":[66],"These":[67],"disparities":[68],"provide":[69],"opportunity":[71],"powerful":[74],"form":[75],"information":[77],"arbitrage--leveraging":[78],"one":[81],"or":[82],"more":[83],"improve":[86],"content":[88],"another.":[90],"Analyzing":[91],"four":[92],"large":[93],"language":[94],"domains":[95],"(English,":[96],"Spanish,":[97],"French,":[98],"German),":[100],"we":[101],"present":[102],"Ziggurat,":[103],"an":[104],"automated":[105],"system":[106],"aligning":[108],"infoboxes,":[110],"creating":[111],"new":[112],"infoboxes":[113],"necessary,":[115],"filling":[116],"missing":[118],"information,":[119],"detecting":[121],"discrepancies":[122],"parallel":[124],"pages.":[125],"Our":[126],"method":[127],"uses":[128],"self-supervised":[129],"learning":[130],"our":[132],"experiments":[133],"demonstrate":[134],"method's":[136],"feasibility,":[137],"even":[138],"absence":[141],"dictionaries.":[143]},"counts_by_year":[{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":4},{"year":2016,"cited_by_count":7},{"year":2015,"cited_by_count":6},{"year":2014,"cited_by_count":7},{"year":2013,"cited_by_count":12},{"year":2012,"cited_by_count":15}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
