{"id":"https://openalex.org/W4412888709","doi":"https://doi.org/10.18653/v1/2025.findings-acl.180","title":"mOSCAR: A Large-scale Multilingual and Multimodal Document-level Corpus","display_name":"mOSCAR: A Large-scale Multilingual and Multimodal Document-level Corpus","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412888709","doi":"https://doi.org/10.18653/v1/2025.findings-acl.180"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.findings-acl.180","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.180","pdf_url":"https://aclanthology.org/2025.findings-acl.180.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":"Findings of the Association for Computational Linguistics: ACL 2025","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.findings-acl.180.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5081921172","display_name":"Matthieu Futeral","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Matthieu Futeral","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091926857","display_name":"Armel Randy Zebaze","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Armel Randy Zebaze","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054913492","display_name":"Pedro Ortiz Su\u00e1rez","orcid":"https://orcid.org/0000-0003-0343-8852"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pedro Ortiz Suarez","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066252626","display_name":"Julien Abadji","orcid":"https://orcid.org/0000-0003-4006-8045"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Julien Abadji","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109961869","display_name":"R\u00e9mi Lacroix","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"R\u00e9mi Lacroix","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109890544","display_name":"Cordelia Schmid","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cordelia Schmid","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046431394","display_name":"Rachel Bawden","orcid":"https://orcid.org/0000-0001-9553-1768"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rachel Bawden","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5077663332","display_name":"Beno\u00eet Sagot","orcid":"https://orcid.org/0000-0002-0107-8526"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Beno\u00eet Sagot","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3461","last_page":"3494"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.978600025177002,"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":0.978600025177002,"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/computer-science","display_name":"Computer science","score":0.7494288682937622},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.6138082146644592},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.553429365158081},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4672417938709259},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3980366885662079},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.3447350859642029},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.13064372539520264},{"id":"https://openalex.org/keywords/cartography","display_name":"Cartography","score":0.0937754213809967}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7494288682937622},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.6138082146644592},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.553429365158081},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4672417938709259},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3980366885662079},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.3447350859642029},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.13064372539520264},{"id":"https://openalex.org/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","level":1,"score":0.0937754213809967}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.18653/v1/2025.findings-acl.180","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.180","pdf_url":"https://aclanthology.org/2025.findings-acl.180.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":"Findings of the Association for Computational Linguistics: ACL 2025","raw_type":"proceedings-article"},{"id":"pmh:oai:HAL:hal-04629451v1","is_oa":true,"landing_page_url":"https://hal.science/hal-04629451","pdf_url":"https://hal.science/hal-04629451/document","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":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"ACL 2025 - Findings of the Association for Computational Linguistics, 2025, Vienna, Austria. pp.3461-3494, &#x27E8;10.18653/v1/2025.findings-acl.180&#x27E9;","raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"pmh:oai:HAL:hal-04629451v2","is_oa":false,"landing_page_url":"https://hal.science/hal-04629451v2/document","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"ACL 2025 - Findings of the Association for Computational Linguistics, Jul 2025, Vienna, Austria. pp.3461-3494, &#x27E8;10.18653/v1/2025.findings-acl.180&#x27E9;","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.findings-acl.180","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.180","pdf_url":"https://aclanthology.org/2025.findings-acl.180.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":"Findings of the Association for Computational Linguistics: ACL 2025","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.5299999713897705}],"awards":[{"id":"https://openalex.org/G5838787665","display_name":"PaRis Artificial Intelligence Research InstitutE","funder_award_id":"ANR-19-P3IA-0001","funder_id":"https://openalex.org/F4320320883","funder_display_name":"Agence Nationale de la Recherche"},{"id":"https://openalex.org/G626190807","display_name":null,"funder_award_id":"19-P3IA-0001","funder_id":"https://openalex.org/F4320320883","funder_display_name":"Agence Nationale de la Recherche"},{"id":"https://openalex.org/G8318455765","display_name":null,"funder_award_id":"ANR-19","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"},{"id":"https://openalex.org/F4320326256","display_name":"Grand \u00c9quipement National De Calcul Intensif","ror":"https://ror.org/0010d1q40"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412888709.pdf","grobid_xml":"https://content.openalex.org/works/W4412888709.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W3188962172","https://openalex.org/W2772917594","https://openalex.org/W4312825515","https://openalex.org/W4306742369","https://openalex.org/W4303457083","https://openalex.org/W2131146434","https://openalex.org/W2951359407","https://openalex.org/W4376623224","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Matthieu":[0],"Futeral,":[1],"Armel":[2],"Randy":[3],"Zebaze,":[4],"Pedro":[5],"Ortiz":[6],"Suarez,":[7],"Julien":[8],"Abadji,":[9],"R\u00e9mi":[10],"Lacroix,":[11],"Cordelia":[12],"Schmid,":[13],"Rachel":[14],"Bawden,":[15],"Beno\u00eet":[16],"Sagot.":[17],"Findings":[18],"of":[19],"the":[20],"Association":[21],"for":[22],"Computational":[23],"Linguistics:":[24],"ACL":[25],"2025.":[26,27]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
