{"id":"https://openalex.org/W1914743126","doi":"https://doi.org/10.18653/v1/w15-3413","title":"LINA: Identifying Comparable Documents from Wikipedia","display_name":"LINA: Identifying Comparable Documents from Wikipedia","publication_year":2015,"publication_date":"2015-01-01","ids":{"openalex":"https://openalex.org/W1914743126","doi":"https://doi.org/10.18653/v1/w15-3413","mag":"1914743126"},"language":"en","primary_location":{"id":"doi:10.18653/v1/w15-3413","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w15-3413","pdf_url":"https://www.aclweb.org/anthology/W15-3413.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":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/W15-3413.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5018688029","display_name":"Emmanuel Morin","orcid":"https://orcid.org/0000-0001-8208-7039"},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I4210165258","display_name":"Laboratoire d'informatique de Nantes Atlantique","ror":"https://ror.org/05487pd16","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1326498283","https://openalex.org/I205703379","https://openalex.org/I4210127572","https://openalex.org/I4210159245","https://openalex.org/I4210165258","https://openalex.org/I97188460"]},{"id":"https://openalex.org/I97188460","display_name":"Nantes Universit\u00e9","ror":"https://ror.org/03gnr7b55","country_code":"FR","type":"education","lineage":["https://openalex.org/I97188460"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Emmanuel Morin","raw_affiliation_strings":["LINA -UMR CNRS 6241, Universit de Nantes, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"LINA -UMR CNRS 6241, Universit de Nantes, France","institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I4210165258","https://openalex.org/I97188460"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Amir Hazem","orcid":null},"institutions":[{"id":"https://openalex.org/I4210108471","display_name":"Le Mans Universit\u00e9","ror":"https://ror.org/01mtcc283","country_code":"FR","type":"education","lineage":["https://openalex.org/I4210108471"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Amir Hazem","raw_affiliation_strings":["LIUM -EA 4023, Universit du Maine, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"LIUM -EA 4023, Universit du Maine, France","institution_ids":["https://openalex.org/I4210108471"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025206208","display_name":"Florian Boudin","orcid":"https://orcid.org/0000-0001-5849-2261"},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I4210165258","display_name":"Laboratoire d'informatique de Nantes Atlantique","ror":"https://ror.org/05487pd16","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1326498283","https://openalex.org/I205703379","https://openalex.org/I4210127572","https://openalex.org/I4210159245","https://openalex.org/I4210165258","https://openalex.org/I97188460"]},{"id":"https://openalex.org/I97188460","display_name":"Nantes Universit\u00e9","ror":"https://ror.org/03gnr7b55","country_code":"FR","type":"education","lineage":["https://openalex.org/I97188460"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Florian Boudin","raw_affiliation_strings":["LINA -UMR CNRS 6241, Universit de Nantes, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"LINA -UMR CNRS 6241, Universit de Nantes, France","institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I4210165258","https://openalex.org/I97188460"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5082175202","display_name":"Elizaveta Loginova-Clouet","orcid":null},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I4210165258","display_name":"Laboratoire d'informatique de Nantes Atlantique","ror":"https://ror.org/05487pd16","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1326498283","https://openalex.org/I205703379","https://openalex.org/I4210127572","https://openalex.org/I4210159245","https://openalex.org/I4210165258","https://openalex.org/I97188460"]},{"id":"https://openalex.org/I97188460","display_name":"Nantes Universit\u00e9","ror":"https://ror.org/03gnr7b55","country_code":"FR","type":"education","lineage":["https://openalex.org/I97188460"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Elizaveta Loginova-Clouet","raw_affiliation_strings":["LINA -UMR CNRS 6241, Universit de Nantes, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"LINA -UMR CNRS 6241, Universit de Nantes, France","institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I4210165258","https://openalex.org/I97188460"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":10,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"88","last_page":"91"},"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":0.9991999864578247,"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":0.9901999831199646,"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":0.6830264329910278},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5271936058998108},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.4306415915489197}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6830264329910278},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5271936058998108},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.4306415915489197}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.18653/v1/w15-3413","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w15-3413","pdf_url":"https://www.aclweb.org/anthology/W15-3413.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:HAL:hal-01185670v1","is_oa":true,"landing_page_url":"https://hal.science/hal-01185670","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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"8th Workshop on Building and Using Comparable Corpora (BUCC), Jul 2015, P\u00e9kin, China","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"doi:10.18653/v1/w15-3413","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w15-3413","pdf_url":"https://www.aclweb.org/anthology/W15-3413.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":0.41999998688697815,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G5241710187","display_name":"Knowledge Rrich Context for Terminology Translation","funder_award_id":"ANR-12-CORD-0020","funder_id":"https://openalex.org/F4320320883","funder_display_name":"Agence Nationale de la Recherche"},{"id":"https://openalex.org/G6702880738","display_name":null,"funder_award_id":"ANR-12","funder_id":"https://openalex.org/F4320320883","funder_display_name":"Agence Nationale de la Recherche"}],"funders":[{"id":"https://openalex.org/F4320320883","display_name":"Agence Nationale de la Recherche","ror":"https://ror.org/00rbzpz17"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W1914743126.pdf","grobid_xml":"https://content.openalex.org/works/W1914743126.grobid-xml"},"referenced_works_count":11,"referenced_works":["https://openalex.org/W8895266","https://openalex.org/W77273554","https://openalex.org/W756467256","https://openalex.org/W1626233182","https://openalex.org/W1726342440","https://openalex.org/W1973152633","https://openalex.org/W2011248508","https://openalex.org/W2102749417","https://openalex.org/W2105673178","https://openalex.org/W2162967019","https://openalex.org/W2163364265"],"related_works":["https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W2382290278","https://openalex.org/W2350741829","https://openalex.org/W2130043461","https://openalex.org/W2530322880"],"abstract_inverted_index":{"This":[0],"paper":[1],"describes":[2],"the":[3,7],"LINA":[4],"system":[5,18],"for":[6],"BUCC":[8],"2015":[9],"shared":[10],"track.":[11],"Following":[12],"(Enright":[13],"and":[14,43],"Kondrak,":[15],"2007),":[16],"our":[17],"identify":[19],"comparable":[20],"documents":[21,39],"by":[22,32],"collecting":[23],"counts":[24],"of":[25],"hapax":[26],"words.":[27],"We":[28],"extend":[29],"this":[30],"method":[31],"filtering":[33],"out":[34],"document":[35],"pairs":[36],"sharing":[37],"target":[38],"using":[40],"pigeonhole":[41],"reasoning":[42],"cross-lingual":[44],"information.":[45]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":2}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}