{"id":"https://openalex.org/W1249771036","doi":"https://doi.org/10.18653/v1/w15-3402","title":"A Factory of Comparable Corpora from Wikipedia","display_name":"A Factory of Comparable Corpora from Wikipedia","publication_year":2015,"publication_date":"2015-01-01","ids":{"openalex":"https://openalex.org/W1249771036","doi":"https://doi.org/10.18653/v1/w15-3402","mag":"1249771036"},"language":"en","primary_location":{"id":"doi:10.18653/v1/w15-3402","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w15-3402","pdf_url":"https://www.aclweb.org/anthology/W15-3402.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Eighth Workshop on Building and Using Comparable Corpora","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/W15-3402.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5067489760","display_name":"Alberto Barr\u00f3n\u2010Cede\u00f1o","orcid":"https://orcid.org/0000-0003-4719-3420"},"institutions":[{"id":"https://openalex.org/I92528248","display_name":"Qatar Foundation","ror":"https://ror.org/01cawbq05","country_code":"QA","type":"funder","lineage":["https://openalex.org/I92528248"]}],"countries":["QA"],"is_corresponding":true,"raw_author_name":"Alberto Barr\u00f3n-Cede\u00f1o","raw_affiliation_strings":["QATAR FOUNDATION"],"affiliations":[{"raw_affiliation_string":"QATAR FOUNDATION","institution_ids":["https://openalex.org/I92528248"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029540488","display_name":"Cristina Espa\u00f1a-Bonet","orcid":"https://orcid.org/0000-0001-5414-4710"},"institutions":[{"id":"https://openalex.org/I92528248","display_name":"Qatar Foundation","ror":"https://ror.org/01cawbq05","country_code":"QA","type":"funder","lineage":["https://openalex.org/I92528248"]}],"countries":["QA"],"is_corresponding":false,"raw_author_name":"Cristina Espa\u00f1a-Bonet","raw_affiliation_strings":["QATAR FOUNDATION"],"affiliations":[{"raw_affiliation_string":"QATAR FOUNDATION","institution_ids":["https://openalex.org/I92528248"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035774486","display_name":"Josu Boldoba","orcid":null},"institutions":[{"id":"https://openalex.org/I9617848","display_name":"Universitat Polit\u00e8cnica de Catalunya","ror":"https://ror.org/03mb6wj31","country_code":"ES","type":"education","lineage":["https://openalex.org/I9617848"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Josu Boldoba","raw_affiliation_strings":["TALP Research Center, Univesitat Politcnica de Catalunya, Barcelona, Spain","Polytechnic University of Catalonia"],"affiliations":[{"raw_affiliation_string":"TALP Research Center, Univesitat Politcnica de Catalunya, Barcelona, Spain","institution_ids":["https://openalex.org/I9617848"]},{"raw_affiliation_string":"Polytechnic University of Catalonia","institution_ids":["https://openalex.org/I9617848"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103372090","display_name":"Llu\u0131\u0301s M\u00e0rquez","orcid":null},"institutions":[{"id":"https://openalex.org/I1301390666","display_name":"Qatar Airways (Qatar)","ror":"https://ror.org/01hx00y13","country_code":"QA","type":"company","lineage":["https://openalex.org/I1301390666"]}],"countries":["QA"],"is_corresponding":false,"raw_author_name":"Llu\u00eds M\u00e0rquez","raw_affiliation_strings":["Qatar Computing Research Institute, HBKU, Doha, Qatar"],"affiliations":[{"raw_affiliation_string":"Qatar Computing Research Institute, HBKU, Doha, Qatar","institution_ids":["https://openalex.org/I1301390666"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5067489760"],"corresponding_institution_ids":["https://openalex.org/I92528248"],"apc_list":null,"apc_paid":null,"fwci":2.6706,"has_fulltext":true,"cited_by_count":28,"citation_normalized_percentile":{"value":0.91305618,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"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":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":0.998199999332428,"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":0.9923999905586243,"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":0.7261179089546204},{"id":"https://openalex.org/keywords/factory","display_name":"Factory (object-oriented programming)","score":0.684015691280365},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.547248125076294},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.43316900730133057},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.40039053559303284},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.18704289197921753}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7261179089546204},{"id":"https://openalex.org/C40149104","wikidata":"https://www.wikidata.org/wiki/Q5620977","display_name":"Factory (object-oriented programming)","level":2,"score":0.684015691280365},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.547248125076294},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.43316900730133057},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40039053559303284},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.18704289197921753}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.18653/v1/w15-3402","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w15-3402","pdf_url":"https://www.aclweb.org/anthology/W15-3402.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Eighth Workshop on Building and Using Comparable Corpora","raw_type":"proceedings-article"},{"id":"pmh:oai:recercat.cat:2072/253961","is_oa":true,"landing_page_url":"http://hdl.handle.net/2117/76611","pdf_url":null,"source":{"id":"https://openalex.org/S4306402147","display_name":"RECERCAT (Consorci de Serveis Universitaris de Catalunya)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210090028","host_organization_name":"Consorci de Serveis Universitaris de Catalunya","host_organization_lineage":["https://openalex.org/I4210090028"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/publishedVersion"}],"best_oa_location":{"id":"doi:10.18653/v1/w15-3402","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w15-3402","pdf_url":"https://www.aclweb.org/anthology/W15-3402.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Eighth Workshop on Building and Using Comparable Corpora","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.8299999833106995,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G4570725529","display_name":null,"funder_award_id":"TIN2012-38523-C02","funder_id":"https://openalex.org/F4320321837","funder_display_name":"Ministerio de Econom\u00eda y Competitividad"}],"funders":[{"id":"https://openalex.org/F4320321837","display_name":"Ministerio de Econom\u00eda y Competitividad","ror":"https://ror.org/034900433"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W1249771036.pdf","grobid_xml":"https://content.openalex.org/works/W1249771036.grobid-xml"},"referenced_works_count":50,"referenced_works":["https://openalex.org/W13944552","https://openalex.org/W14574270","https://openalex.org/W22168010","https://openalex.org/W44018397","https://openalex.org/W58646613","https://openalex.org/W71111251","https://openalex.org/W98191119","https://openalex.org/W107230253","https://openalex.org/W108460122","https://openalex.org/W232456582","https://openalex.org/W316763119","https://openalex.org/W630532510","https://openalex.org/W1499239271","https://openalex.org/W1523140216","https://openalex.org/W1535555350","https://openalex.org/W1543107604","https://openalex.org/W1543317902","https://openalex.org/W1549114989","https://openalex.org/W1599610669","https://openalex.org/W1626233182","https://openalex.org/W1631260214","https://openalex.org/W1726342440","https://openalex.org/W1869906767","https://openalex.org/W1916559533","https://openalex.org/W1994500780","https://openalex.org/W2029097226","https://openalex.org/W2053154970","https://openalex.org/W2098162425","https://openalex.org/W2101096097","https://openalex.org/W2101105183","https://openalex.org/W2105673178","https://openalex.org/W2119188105","https://openalex.org/W2124807415","https://openalex.org/W2128951443","https://openalex.org/W2138397390","https://openalex.org/W2139812240","https://openalex.org/W2141068210","https://openalex.org/W2146574666","https://openalex.org/W2156985047","https://openalex.org/W2167265720","https://openalex.org/W2277589743","https://openalex.org/W2404602200","https://openalex.org/W2588710172","https://openalex.org/W2595715041","https://openalex.org/W2768311607","https://openalex.org/W2949769632","https://openalex.org/W3103151093","https://openalex.org/W3197645311","https://openalex.org/W3211848854","https://openalex.org/W4213169074"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W2384486034","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W2382290278","https://openalex.org/W2350741829","https://openalex.org/W2530322880","https://openalex.org/W1596801655"],"abstract_inverted_index":{"Multiple":[0],"approaches":[1],"to":[2,13,52,71],"grab":[3],"comparable":[4,21,39,66],"data":[5],"from":[6,48,64],"the":[7,35,54,57,65,83,87],"Web":[8],"have":[9],"been":[10],"developed":[11],"up":[12],"date.":[14],"Nevertheless,":[15],"coming":[16],"out":[17],"with":[18],"a":[19,24,32,104],"high-quality":[20],"corpus":[22],"of":[23,38,56,89],"specific":[25,46,78],"topic":[26],"is":[27],"not":[28],"straightforward.":[29],"We":[30],"present":[31],"model":[33],"for":[34,77],"automatic":[36],"extraction":[37],"texts":[40],"in":[41,86],"multiple":[42],"languages":[43],"and":[44,68,93],"on":[45,82],"topics":[47],"Wikipedia.":[49],"In":[50],"order":[51],"prove":[53],"value":[55],"model,":[58],"we":[59,113],"automatically":[60],"extract":[61],"parallel":[62],"sentences":[63],"collections":[67],"use":[69],"them":[70],"train":[72],"statistical":[73],"machine":[74],"translation":[75],"engines":[76],"domains.":[79],"Our":[80],"experiments":[81],"English-Spanish":[84],"pair":[85],"domains":[88],"Computer":[90],"Science,":[91,92],"Sports":[94],"show":[95,114],"that":[96,115],"our":[97],"in-domain":[98,109],"translator":[99],"performs":[100],"significantly":[101],"better":[102],"than":[103],"generic":[105],"one":[106],"when":[107,120],"translating":[108,121],"Wikipedia":[110],"articles.":[111],"Moreover,":[112],"these":[116],"corpora":[117],"can":[118],"help":[119],"out-of-domain":[122],"texts.":[123]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":6},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":3}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}