{"id":"https://openalex.org/W2970814728","doi":"https://doi.org/10.18653/v1/w19-4619","title":"OSIAN: Open Source International Arabic News Corpus - Preparation and Integration into the CLARIN-infrastructure","display_name":"OSIAN: Open Source International Arabic News Corpus - Preparation and Integration into the CLARIN-infrastructure","publication_year":2019,"publication_date":"2019-01-01","ids":{"openalex":"https://openalex.org/W2970814728","doi":"https://doi.org/10.18653/v1/w19-4619","mag":"2970814728"},"language":"en","primary_location":{"id":"doi:10.18653/v1/w19-4619","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w19-4619","pdf_url":"https://www.aclweb.org/anthology/W19-4619.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 Fourth Arabic Natural Language Processing Workshop","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/W19-4619.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5043920765","display_name":"Imad Zeroual","orcid":"https://orcid.org/0000-0002-4454-6369"},"institutions":[{"id":"https://openalex.org/I4210108110","display_name":"Mohamed I University","ror":"https://ror.org/01ejxf797","country_code":"MA","type":"education","lineage":["https://openalex.org/I4210108110"]}],"countries":["MA"],"is_corresponding":false,"raw_author_name":"Imad Zeroual","raw_affiliation_strings":["Computer Sciences Laboratory, Mohamed First University, Morocco"],"affiliations":[{"raw_affiliation_string":"Computer Sciences Laboratory, Mohamed First University, Morocco","institution_ids":["https://openalex.org/I4210108110"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026938360","display_name":"Dirk Goldhahn","orcid":"https://orcid.org/0000-0003-1681-567X"},"institutions":[{"id":"https://openalex.org/I926574661","display_name":"Leipzig University","ror":"https://ror.org/03s7gtk40","country_code":"DE","type":"education","lineage":["https://openalex.org/I926574661"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Dirk Goldhahn","raw_affiliation_strings":["Natural Language Processing Group, University of Leipzig, German"],"affiliations":[{"raw_affiliation_string":"Natural Language Processing Group, University of Leipzig, German","institution_ids":["https://openalex.org/I926574661"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088513557","display_name":"Thomas Eckart","orcid":"https://orcid.org/0000-0001-6692-0713"},"institutions":[{"id":"https://openalex.org/I926574661","display_name":"Leipzig University","ror":"https://ror.org/03s7gtk40","country_code":"DE","type":"education","lineage":["https://openalex.org/I926574661"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Thomas Eckart","raw_affiliation_strings":["Natural Language Processing Group, University of Leipzig, German"],"affiliations":[{"raw_affiliation_string":"Natural Language Processing Group, University of Leipzig, German","institution_ids":["https://openalex.org/I926574661"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5036610488","display_name":"Abdelhak Lakhouaja","orcid":"https://orcid.org/0000-0001-9626-5377"},"institutions":[{"id":"https://openalex.org/I4210108110","display_name":"Mohamed I University","ror":"https://ror.org/01ejxf797","country_code":"MA","type":"education","lineage":["https://openalex.org/I4210108110"]}],"countries":["MA"],"is_corresponding":true,"raw_author_name":"Abdelhak Lakhouaja","raw_affiliation_strings":["Computer Sciences Laboratory, Mohamed First University, Morocco"],"affiliations":[{"raw_affiliation_string":"Computer Sciences Laboratory, Mohamed First University, Morocco","institution_ids":["https://openalex.org/I4210108110"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5036610488"],"corresponding_institution_ids":["https://openalex.org/I4210108110"],"apc_list":null,"apc_paid":null,"fwci":6.3654,"has_fulltext":true,"cited_by_count":87,"citation_normalized_percentile":{"value":0.97178313,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"175","last_page":"182"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9975000023841858,"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":0.9975000023841858,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9916999936103821,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T13523","display_name":"Mathematics, Computing, and Information Processing","score":0.9894000291824341,"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/computer-science","display_name":"Computer science","score":0.7993204593658447},{"id":"https://openalex.org/keywords/metadata","display_name":"Metadata","score":0.5764050483703613},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.537425696849823},{"id":"https://openalex.org/keywords/xml","display_name":"XML","score":0.522063672542572},{"id":"https://openalex.org/keywords/license","display_name":"License","score":0.5086108446121216},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.4543669521808624},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.23610559105873108}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7993204593658447},{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.5764050483703613},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.537425696849823},{"id":"https://openalex.org/C8797682","wikidata":"https://www.wikidata.org/wiki/Q2115","display_name":"XML","level":2,"score":0.522063672542572},{"id":"https://openalex.org/C2780560020","wikidata":"https://www.wikidata.org/wiki/Q79719","display_name":"License","level":2,"score":0.5086108446121216},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.4543669521808624},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.23610559105873108},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/w19-4619","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w19-4619","pdf_url":"https://www.aclweb.org/anthology/W19-4619.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 Fourth Arabic Natural Language Processing Workshop","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/w19-4619","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w19-4619","pdf_url":"https://www.aclweb.org/anthology/W19-4619.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 Fourth Arabic Natural Language Processing Workshop","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9","score":0.5899999737739563}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2970814728.pdf","grobid_xml":"https://content.openalex.org/works/W2970814728.grobid-xml"},"referenced_works_count":16,"referenced_works":["https://openalex.org/W179850243","https://openalex.org/W321015332","https://openalex.org/W973829271","https://openalex.org/W1600700896","https://openalex.org/W2074488411","https://openalex.org/W2119070361","https://openalex.org/W2250600805","https://openalex.org/W2415084581","https://openalex.org/W2465804994","https://openalex.org/W2473221880","https://openalex.org/W2570920354","https://openalex.org/W2594145042","https://openalex.org/W2770458778","https://openalex.org/W2789386281","https://openalex.org/W2791757336","https://openalex.org/W2805305203"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W2606446052","https://openalex.org/W2036021480","https://openalex.org/W2392768766","https://openalex.org/W2058118494","https://openalex.org/W2361861616","https://openalex.org/W2095118173","https://openalex.org/W2382021449","https://openalex.org/W2263699433","https://openalex.org/W2251247982"],"abstract_inverted_index":{"The":[0,35,74,91,131],"World":[1],"Wide":[2],"Web":[3],"has":[4],"become":[5],"a":[6,30],"fundamental":[7],"resource":[8],"for":[9,33],"building":[10],"large":[11],"text":[12],"corpora.":[13,58],"Broadcasting":[14],"platforms":[15],"such":[16],"as":[17],"news":[18,82],"websites":[19],"are":[20],"rich":[21],"sources":[22],"of":[23,53,55,65,94],"data":[24,76],"regarding":[25],"diverse":[26],"topics":[27],"and":[28,105,129,137],"form":[29],"valuable":[31],"foundation":[32],"research.":[34],"Arabic":[36,45,70,81],"language":[37,50],"is":[38,46,111,117,125,134],"extensively":[39],"utilized":[40],"on":[41,88],"the":[42,62,66,89,140],"Web.":[43,90],"Still,":[44],"relatively":[47],"an":[48],"under-resourced":[49],"in":[51,113],"terms":[52],"availability":[54],"freely":[56,86],"annotated":[57,118,126],"This":[59],"paper":[60],"presents":[61],"first":[63],"version":[64],"Open":[67],"Source":[68],"International":[69],"News":[71],"(OSIAN)":[72],"corpus.":[73],"corpus":[75,92,133],"was":[77],"collected":[78],"from":[79],"international":[80],"websites,":[83],"all":[84],"being":[85],"available":[87],"consists":[93],"about":[95],"3.5":[96],"million":[97,103],"articles":[98],"comprising":[99],"more":[100],"than":[101],"37":[102],"sentences":[104],"roughly":[106],"1":[107],"billion":[108],"tokens.":[109],"It":[110],"encoded":[112],"XML;":[114],"each":[115,123],"article":[116],"with":[119,127],"metadata":[120],"information.":[121],"Moreover,":[122],"word":[124],"lemma":[128],"part-ofspeech.":[130],"described":[132],"processed,":[135],"archived":[136],"published":[138],"into":[139],"CLARIN":[141],"infrastructure.":[142]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":11},{"year":2024,"cited_by_count":13},{"year":2023,"cited_by_count":18},{"year":2022,"cited_by_count":19},{"year":2021,"cited_by_count":14},{"year":2020,"cited_by_count":10}],"updated_date":"2026-03-21T08:13:44.787528","created_date":"2025-10-10T00:00:00"}
