{"id":"https://openalex.org/W2045117606","doi":"https://doi.org/10.1145/1147197.1147210","title":"The Wikipedia XML corpus","display_name":"The Wikipedia XML corpus","publication_year":2006,"publication_date":"2006-06-01","ids":{"openalex":"https://openalex.org/W2045117606","doi":"https://doi.org/10.1145/1147197.1147210","mag":"2045117606"},"language":"en","primary_location":{"id":"doi:10.1145/1147197.1147210","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1147197.1147210","pdf_url":null,"source":{"id":"https://openalex.org/S6756005","display_name":"ACM SIGIR Forum","issn_l":"0163-5840","issn":["0163-5840","1558-0229"],"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":"ACM SIGIR Forum","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":null,"display_name":"Ludovic Denoyer","orcid":null},"institutions":[{"id":"https://openalex.org/I4210159731","display_name":"Laboratoire de Recherche en Informatique de Paris 6","ror":"https://ror.org/05krcen59","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I39804081","https://openalex.org/I4210159245","https://openalex.org/I4210159731"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"Ludovic Denoyer","raw_affiliation_strings":["Laboratoire d'Informatique de Paris, Paris"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Laboratoire d'Informatique de Paris, Paris","institution_ids":["https://openalex.org/I4210159731"]}]},{"author_position":"last","author":{"id":null,"display_name":"Patrick Gallinari","orcid":null},"institutions":[{"id":"https://openalex.org/I4210159731","display_name":"Laboratoire de Recherche en Informatique de Paris 6","ror":"https://ror.org/05krcen59","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I39804081","https://openalex.org/I4210159245","https://openalex.org/I4210159731"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Patrick Gallinari","raw_affiliation_strings":["Laboratoire d'Informatique de Paris, Paris"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Laboratoire d'Informatique de Paris, Paris","institution_ids":["https://openalex.org/I4210159731"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210159731"],"apc_list":null,"apc_paid":null,"fwci":62.1884,"has_fulltext":false,"cited_by_count":195,"citation_normalized_percentile":{"value":0.99946818,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"40","issue":"1","first_page":"64","last_page":"69"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12478","display_name":"Wikis in Education and Collaboration","score":0.48190000653266907,"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":0.48190000653266907,"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/T12377","display_name":"Digital Humanities and Scholarship","score":0.0689999982714653,"subfield":{"id":"https://openalex.org/subfields/1208","display_name":"Literature and Literary Theory"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T13523","display_name":"Mathematics, Computing, and Information Processing","score":0.023000000044703484,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/encyclopedia","display_name":"Encyclopedia","score":0.9175999760627747},{"id":"https://openalex.org/keywords/markup-language","display_name":"Markup language","score":0.7703999876976013},{"id":"https://openalex.org/keywords/xml","display_name":"XML","score":0.6363999843597412},{"id":"https://openalex.org/keywords/sgml","display_name":"SGML","score":0.48019999265670776},{"id":"https://openalex.org/keywords/ruleml","display_name":"RuleML","score":0.47450000047683716},{"id":"https://openalex.org/keywords/document-type-definition","display_name":"Document type definition","score":0.46630001068115234}],"concepts":[{"id":"https://openalex.org/C148863701","wikidata":"https://www.wikidata.org/wiki/Q5292","display_name":"Encyclopedia","level":2,"score":0.9175999760627747},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7850000262260437},{"id":"https://openalex.org/C45874996","wikidata":"https://www.wikidata.org/wiki/Q37045","display_name":"Markup language","level":3,"score":0.7703999876976013},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.6608999967575073},{"id":"https://openalex.org/C8797682","wikidata":"https://www.wikidata.org/wiki/Q2115","display_name":"XML","level":2,"score":0.6363999843597412},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5185999870300293},{"id":"https://openalex.org/C62701983","wikidata":"https://www.wikidata.org/wiki/Q207819","display_name":"SGML","level":4,"score":0.48019999265670776},{"id":"https://openalex.org/C196388810","wikidata":"https://www.wikidata.org/wiki/Q631877","display_name":"RuleML","level":5,"score":0.47450000047683716},{"id":"https://openalex.org/C84314905","wikidata":"https://www.wikidata.org/wiki/Q212327","display_name":"Document type definition","level":4,"score":0.46630001068115234},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3612000048160553},{"id":"https://openalex.org/C189139006","wikidata":"https://www.wikidata.org/wiki/Q166074","display_name":"XHTML","level":4,"score":0.31529998779296875},{"id":"https://openalex.org/C138708601","wikidata":"https://www.wikidata.org/wiki/Q8811","display_name":"HTML","level":3,"score":0.2992999851703644},{"id":"https://openalex.org/C18599908","wikidata":"https://www.wikidata.org/wiki/Q1196904","display_name":"Electronic publishing","level":3,"score":0.2757999897003174},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.27219998836517334},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.2685000002384186},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.25519999861717224}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/1147197.1147210","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1147197.1147210","pdf_url":null,"source":{"id":"https://openalex.org/S6756005","display_name":"ACM SIGIR Forum","issn_l":"0163-5840","issn":["0163-5840","1558-0229"],"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":"ACM SIGIR Forum","raw_type":"journal-article"},{"id":"pmh:oai:HAL:hal-01172244v1","is_oa":false,"landing_page_url":"https://hal.science/hal-01172244","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Sigir Forum, 2006, 40 (1), pp.64-69. &#x27E8;10.1145/1147197.1147210&#x27E9;","raw_type":"Journal articles"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Wikipedia":[0],"is":[1,35],"a":[2,22,28],"well":[3],"known":[4],"free":[5],"content,":[6],"multilingual":[7],"encyclopedia":[8,34],"written":[9],"collaboratively":[10],"by":[11],"contributors":[12],"around":[13],"the":[14],"world.":[15],"Anybody":[16],"can":[17],"edit":[18],"an":[19],"article":[20],"using":[21],"wiki":[23],"markup":[24],"language":[25],"that":[26],"offers":[27],"simplified":[29],"alternative":[30],"to":[31],"HTML.":[32],"This":[33],"composed":[36],"of":[37,39],"millions":[38],"articles":[40],"in":[41],"different":[42],"languages.":[43]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":6},{"year":2013,"cited_by_count":6},{"year":2012,"cited_by_count":8}],"updated_date":"2026-04-28T14:05:53.105641","created_date":"2016-06-24T00:00:00"}
