{"id":"https://openalex.org/W40305183","doi":"https://doi.org/10.63317/4uqppbbzs9c9","title":"Semantically Annotated Snapshot of the English Wikipedia","display_name":"Semantically Annotated Snapshot of the English Wikipedia","publication_year":2008,"publication_date":"2008-05-01","ids":{"openalex":"https://openalex.org/W40305183","doi":"https://doi.org/10.63317/4uqppbbzs9c9","mag":"40305183"},"language":"en","primary_location":{"id":"doi:10.63317/4uqppbbzs9c9","doi":"https://doi.org/10.63317/4uqppbbzs9c9","is_oa":true,"landing_page_url":"https://doi.org/10.63317/4uqppbbzs9c9","pdf_url":null,"source":{"id":"https://openalex.org/S7407088301","display_name":"Language Resources and Evaluation Conference (LREC)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Language Resources and Evaluation Conference","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.63317/4uqppbbzs9c9","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5001177249","display_name":"Jordi Atserias","orcid":"https://orcid.org/0000-0002-4604-5541","observed_orcids":["https://orcid.org/0000-0002-4604-5541"]},"institutions":[{"id":"https://openalex.org/I169108374","display_name":"University of the Basque Country","ror":"https://ror.org/000xsnr85","country_code":"ES","type":"education","lineage":["https://openalex.org/I169108374"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Jordi Atserias","raw_affiliation_strings":["University of the Basque Country, Leioa, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of the Basque Country, Leioa, Spain","institution_ids":["https://openalex.org/I169108374"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086495684","display_name":"Hugo Zaragoza","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I1325784139","display_name":"Yahoo (United Kingdom)","ror":"https://ror.org/038p3gq39","country_code":"GB","type":"company","lineage":["https://openalex.org/I1325784139","https://openalex.org/I4210134091"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Hugo Zaragoza","raw_affiliation_strings":["Yahoo (United Kingdom), London, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Yahoo (United Kingdom), London, United Kingdom","institution_ids":["https://openalex.org/I1325784139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009724893","display_name":"Massimiliano Ciaramita","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I1325784139","display_name":"Yahoo (United Kingdom)","ror":"https://ror.org/038p3gq39","country_code":"GB","type":"company","lineage":["https://openalex.org/I1325784139","https://openalex.org/I4210134091"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Massimiliano Ciaramita","raw_affiliation_strings":["Yahoo (United Kingdom), London, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Yahoo (United Kingdom), London, United Kingdom","institution_ids":["https://openalex.org/I1325784139"]}]},{"author_position":"last","author":{"id":null,"display_name":"Giuseppe Attardi","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I55143463","display_name":"University of Turin","ror":"https://ror.org/048tbm396","country_code":"IT","type":"education","lineage":["https://openalex.org/I55143463"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Giuseppe Attardi","raw_affiliation_strings":["University of Turin, Turin, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Turin, Turin, Italy","institution_ids":["https://openalex.org/I55143463"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":8.1735,"has_fulltext":true,"cited_by_count":45,"citation_normalized_percentile":{"value":0.9827542,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9463000297546387,"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":0.9463000297546387,"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":0.03420000150799751,"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/T10215","display_name":"Semantic Web and Ontologies","score":0.016300000250339508,"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/wikipedia","display_name":"Wikipedia","score":0.7770000100135803},{"id":"https://openalex.org/keywords/semantic-annotation","display_name":"semantic annotation","score":0.8460000157356262},{"id":"https://openalex.org/keywords/syntactic-annotation","display_name":"syntactic annotation","score":0.7720000147819519},{"id":"https://openalex.org/keywords/reference-corpus","display_name":"reference corpus","score":0.7839999794960022},{"id":"https://openalex.org/keywords/english-wikipedia","display_name":"English Wikipedia","score":0.503000020980835},{"id":"https://openalex.org/keywords/natural-language-processing-resources","display_name":"natural language processing resources","score":0.5429999828338623}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8813781142234802},{"id":"https://openalex.org/C55282118","wikidata":"https://www.wikidata.org/wiki/Q252683","display_name":"Snapshot (computer storage)","level":2,"score":0.669359564781189},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6323943138122559},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5634248852729797},{"id":"https://openalex.org/C56666940","wikidata":"https://www.wikidata.org/wiki/Q788790","display_name":"Documentation","level":2,"score":0.5097972750663757},{"id":"https://openalex.org/C2777889803","wikidata":"https://www.wikidata.org/wiki/Q25047676","display_name":"Named entity","level":2,"score":0.5085238218307495},{"id":"https://openalex.org/C2780560020","wikidata":"https://www.wikidata.org/wiki/Q79719","display_name":"License","level":2,"score":0.5037416815757751},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.48006924986839294},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.474693238735199},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.09507668018341064},{"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.63317/4uqppbbzs9c9","doi":"https://doi.org/10.63317/4uqppbbzs9c9","is_oa":true,"landing_page_url":"https://doi.org/10.63317/4uqppbbzs9c9","pdf_url":null,"source":{"id":"https://openalex.org/S7407088301","display_name":"Language Resources and Evaluation Conference (LREC)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Language Resources and Evaluation Conference","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.157.9723","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.157.9723","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.lrec-conf.org/proceedings/lrec2008/pdf/581_paper.pdf","raw_type":"text"},{"id":"mag:40305183","doi":null,"is_oa":false,"landing_page_url":"http://www.lrec-conf.org/proceedings/lrec2008/pdf/581_paper.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306424877","display_name":"Language Resources and Evaluation","issn_l":"1574-020X","issn":["1574-020X","1574-0218"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["anvur-class-a","anvur-scientific","cwts-core","dongbi-c","erih-plus","jufo-3","norway-2","poland-70","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":"Language Resources and Evaluation","raw_type":null}],"best_oa_location":{"id":"doi:10.63317/4uqppbbzs9c9","doi":"https://doi.org/10.63317/4uqppbbzs9c9","is_oa":true,"landing_page_url":"https://doi.org/10.63317/4uqppbbzs9c9","pdf_url":null,"source":{"id":"https://openalex.org/S7407088301","display_name":"Language Resources and Evaluation Conference (LREC)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Language Resources and Evaluation Conference","raw_type":"proceedings-article"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[{"id":"https://metadata.un.org/sdg/4","score":0.4300000071525574,"display_name":"Quality education"}],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W59145111","https://openalex.org/W1580825123","https://openalex.org/W2051390224","https://openalex.org/W2065157922","https://openalex.org/W2093647425","https://openalex.org/W2120779048","https://openalex.org/W2144578941","https://openalex.org/W2147268363"],"related_works":["https://openalex.org/W170175252","https://openalex.org/W2578698629","https://openalex.org/W2140428995","https://openalex.org/W7097178460","https://openalex.org/W2038901175","https://openalex.org/W2271609058","https://openalex.org/W1126025630","https://openalex.org/W7096519346","https://openalex.org/W580844164","https://openalex.org/W2250741443"],"abstract_inverted_index":{"This":[0],"paper":[1],"describes":[2],"SW1,":[3],"the":[4,13,27,34,53,64,131],"first":[5],"version":[6],"of":[7,12,61,66,69,82,97],"a":[8,22,59,105,117,122],"semantically":[9,118],"annotated":[10,119],"snapshot":[11],"English":[14],"Wikipedia.":[15],"In":[16],"recent":[17],"years":[18],"Wikipedia":[19,44,70],"has":[20],"become":[21],"valuable":[23],"resource":[24],"for":[25,42,95],"both":[26,98],"Natural":[28],"Language":[29],"Processing":[30],"(NLP)":[31],"community":[32],"and":[33,50,92,100,111,121,136],"Information":[35],"Retrieval":[36],"(IR)":[37],"community.":[38],"Although":[39],"NLP":[40,99],"technology":[41],"processing":[43],"already":[45],"exists,":[46],"not":[47],"all":[48],"researchers":[49,96],"developers":[51],"have":[52],"computational":[54],"resources":[55],"to":[56,77,86,90,108],"process":[57],"such":[58],"volume":[60],"information.":[62],"Moreover,":[63],"use":[65],"different":[67],"versions":[68],"processed":[71],"differently":[72],"might":[73],"make":[74,112],"it":[75],"difficult":[76],"compare":[78],"results.":[79],"The":[80],"aim":[81],"this":[83],"work":[84],"is":[85],"provide":[87],"easy":[88],"access":[89],"syntactic":[91],"semantic":[93],"annotations":[94],"IR":[101],"communities":[102],"by":[103],"building":[104],"reference":[106],"corpus":[107,120],"homogenize":[109],"experiments":[110],"results":[113],"comparable.":[114],"These":[115],"resources,":[116],"\u201centity":[123],"containment":[124],"\u201d":[125],"derived":[126],"graph,":[127],"are":[128],"licensed":[129],"under":[130],"GNU":[132],"Free":[133],"Documentation":[134],"License":[135],"available":[137],"from":[138]},"counts_by_year":[{"year":2016,"cited_by_count":5},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":2}],"updated_date":"2026-10-14T16:39:01.820549","created_date":"2016-06-24T00:00:00"}
