{"id":"https://openalex.org/W1985583527","doi":"https://doi.org/10.1145/1999676.1999703","title":"Language resources extracted from Wikipedia","display_name":"Language resources extracted from Wikipedia","publication_year":2011,"publication_date":"2011-06-26","ids":{"openalex":"https://openalex.org/W1985583527","doi":"https://doi.org/10.1145/1999676.1999703","mag":"1985583527"},"language":"en","primary_location":{"id":"doi:10.1145/1999676.1999703","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1999676.1999703","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the sixth international conference on Knowledge capture","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/A5111465891","display_name":"Denny Vrande\u010di\u0107","orcid":null},"institutions":[{"id":"https://openalex.org/I4210137741","display_name":"Wikimedia Deutschland","ror":"https://ror.org/03e9gte70","country_code":"DE","type":"nonprofit","lineage":["https://openalex.org/I4210137741"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Denny Vrandeci\u0107","raw_affiliation_strings":["KIT and Wikimedia Deutschland, Karlsruhe and Berlin, Germany"],"affiliations":[{"raw_affiliation_string":"KIT and Wikimedia Deutschland, Karlsruhe and Berlin, Germany","institution_ids":["https://openalex.org/I4210137741"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038304632","display_name":"Philipp Sorg","orcid":null},"institutions":[{"id":"https://openalex.org/I102335020","display_name":"Karlsruhe Institute of Technology","ror":"https://ror.org/04t3en479","country_code":"DE","type":"education","lineage":["https://openalex.org/I102335020","https://openalex.org/I1305996414"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Philipp Sorg","raw_affiliation_strings":["KIT, Karlsruhe, Germany","KIT,#N#Karlsruhe, Germany"],"affiliations":[{"raw_affiliation_string":"KIT, Karlsruhe, Germany","institution_ids":["https://openalex.org/I102335020"]},{"raw_affiliation_string":"KIT,#N#Karlsruhe, Germany","institution_ids":["https://openalex.org/I102335020"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5039385406","display_name":"Rudi Studer","orcid":null},"institutions":[{"id":"https://openalex.org/I102335020","display_name":"Karlsruhe Institute of Technology","ror":"https://ror.org/04t3en479","country_code":"DE","type":"education","lineage":["https://openalex.org/I102335020","https://openalex.org/I1305996414"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Rudi Studer","raw_affiliation_strings":["KIT, Karlsruhe, Germany","KIT,#N#Karlsruhe, Germany"],"affiliations":[{"raw_affiliation_string":"KIT, Karlsruhe, Germany","institution_ids":["https://openalex.org/I102335020"]},{"raw_affiliation_string":"KIT,#N#Karlsruhe, Germany","institution_ids":["https://openalex.org/I102335020"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5111465891"],"corresponding_institution_ids":["https://openalex.org/I4210137741"],"apc_list":null,"apc_paid":null,"fwci":0.4386,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.71772636,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"5","issue":null,"first_page":"153","last_page":"160"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":1.0,"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":1.0,"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":0.9994999766349792,"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":0.9950000047683716,"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":0.8950772285461426},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.681188702583313},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6009448766708374},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.548489511013031},{"id":"https://openalex.org/keywords/term","display_name":"Term (time)","score":0.4800106883049011},{"id":"https://openalex.org/keywords/simple","display_name":"Simple (philosophy)","score":0.47893863916397095},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.40988314151763916}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8950772285461426},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.681188702583313},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6009448766708374},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.548489511013031},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.4800106883049011},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.47893863916397095},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.40988314151763916},{"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},{"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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/1999676.1999703","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1999676.1999703","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the sixth international conference on Knowledge capture","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.372.6793","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.372.6793","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.aifb.kit.edu/images/5/5c/Vrandecic11language.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7699999809265137,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W22168010","https://openalex.org/W58646613","https://openalex.org/W582406943","https://openalex.org/W1499239271","https://openalex.org/W1965555277","https://openalex.org/W1972594981","https://openalex.org/W1975051470","https://openalex.org/W2075843680","https://openalex.org/W2146950091","https://openalex.org/W2155870214","https://openalex.org/W2423725643"],"related_works":["https://openalex.org/W1585007175","https://openalex.org/W2382521049","https://openalex.org/W2144385241","https://openalex.org/W4300101996","https://openalex.org/W2165950148","https://openalex.org/W4253593777","https://openalex.org/W2951497643","https://openalex.org/W4403053866","https://openalex.org/W2142393343","https://openalex.org/W2338854850"],"abstract_inverted_index":{"Wikipedia":[0,38,49],"provides":[1],"an":[2],"interesting":[3],"amount":[4],"of":[5,37,88,115],"text":[6],"for":[7,104],"more":[8],"than":[9],"hundred":[10],"languages.":[11,41],"This":[12],"also":[13],"includes":[14],"languages":[15],"where":[16],"no":[17],"reference":[18],"corpora":[19],"or":[20],"other":[21,57],"linguistic":[22],"resources":[23],"are":[24,50,74],"easily":[25],"available.":[26],"We":[27,78],"have":[28],"extracted":[29],"background":[30],"language":[31,53,90],"models":[32,43,54,64,91],"built":[33],"from":[34,45,56],"the":[35,63,82,89,100,108],"content":[36],"in":[39,65],"various":[40],"The":[42,60,97],"generated":[44],"Simple":[46],"and":[47,72,76,85,107],"English":[48],"compared":[51],"to":[52,67,81],"derived":[55],"established":[58],"corpora.":[59],"differences":[61],"between":[62],"regard":[66],"term":[68,70],"coverage,":[69],"distribution":[71],"correlation":[73],"described":[75],"discussed.":[77],"provide":[79,112],"access":[80],"full":[83],"dataset":[84,103],"create":[86],"visualizations":[87],"that":[92,110],"can":[93],"be":[94],"used":[95],"exploratory.":[96],"paper":[98],"describes":[99],"newly":[101],"released":[102],"33":[105],"languages,":[106],"services":[109],"we":[111],"on":[113],"top":[114],"them.":[116]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}
