{"id":"https://openalex.org/W7140078077","doi":"https://doi.org/10.18653/v1/2026.vardial-1.23","title":"OpenLID-v3: Improving the Precision of Closely Related Language Identification \u2013 An Experience Report","display_name":"OpenLID-v3: Improving the Precision of Closely Related Language Identification \u2013 An Experience Report","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7140078077","doi":"https://doi.org/10.18653/v1/2026.vardial-1.23"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.vardial-1.23","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.vardial-1.23","pdf_url":"https://aclanthology.org/2026.vardial-1.23.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 13th Workshop on NLP for Similar Languages, Varieties and Dialects","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.vardial-1.23.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Mariia Fedorova","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mariia Fedorova","raw_affiliation_strings":["Language Technology Group Department of Informatics University of Oslo"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Language Technology Group Department of Informatics University of Oslo","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Nikolay Arefyev","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nikolay Arefyev","raw_affiliation_strings":["Language Technology Group Department of Informatics University of Oslo"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Language Technology Group Department of Informatics University of Oslo","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Maja Buljan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Maja Buljan","raw_affiliation_strings":["Language Technology Group Department of Informatics University of Oslo"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Language Technology Group Department of Informatics University of Oslo","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jind\u0159ich Helcl","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jind\u0159ich Helcl","raw_affiliation_strings":["Language Technology Group Department of Informatics University of Oslo"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Language Technology Group Department of Informatics University of Oslo","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Stephan Oepen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Stephan Oepen","raw_affiliation_strings":["Language Technology Group Department of Informatics University of Oslo"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Language Technology Group Department of Informatics University of Oslo","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Egil R\u00f8nningstad","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Egil R\u00f8nningstad","raw_affiliation_strings":["Language Technology Group Department of Informatics University of Oslo"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Language Technology Group Department of Informatics University of Oslo","institution_ids":[]}]},{"author_position":"last","author":{"id":null,"display_name":"Yves Scherrer","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yves Scherrer","raw_affiliation_strings":["Language Technology Group Department of Informatics University of Oslo"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Language Technology Group Department of Informatics University of Oslo","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":7,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.36745334,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"275","last_page":"292"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12380","display_name":"Authorship Attribution and Profiling","score":0.9423999786376953,"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/T12380","display_name":"Authorship Attribution and Profiling","score":0.9423999786376953,"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/T13629","display_name":"Text Readability and Simplification","score":0.021199999377131462,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.00839999970048666,"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/identification","display_name":"Identification (biology)","score":0.45899999141693115},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.335099995136261},{"id":"https://openalex.org/keywords/language-identification","display_name":"Language identification","score":0.28290000557899475},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.27160000801086426},{"id":"https://openalex.org/keywords/language-understanding","display_name":"Language understanding","score":0.2662000060081482}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6309000253677368},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5092999935150146},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.49810001254081726},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.45899999141693115},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.335099995136261},{"id":"https://openalex.org/C129792486","wikidata":"https://www.wikidata.org/wiki/Q1050419","display_name":"Language identification","level":3,"score":0.28290000557899475},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.27709999680519104},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.27160000801086426},{"id":"https://openalex.org/C2983448237","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Language understanding","level":2,"score":0.2662000060081482},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.2531000077724457}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.18653/v1/2026.vardial-1.23","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.vardial-1.23","pdf_url":"https://aclanthology.org/2026.vardial-1.23.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 13th Workshop on NLP for Similar Languages, Varieties and Dialects","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2602.13139","is_oa":true,"landing_page_url":"https://arxiv.org/abs/2602.13139","pdf_url":"https://arxiv.org/pdf/2602.13139","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.vardial-1.23","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.vardial-1.23","pdf_url":"https://aclanthology.org/2026.vardial-1.23.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 13th Workshop on NLP for Similar Languages, Varieties and Dialects","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5112024542","display_name":"High Performance Language Technologies","funder_award_id":"101070350","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"}],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320334322","display_name":"HORIZON EUROPE Framework Programme","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7140078077.pdf","grobid_xml":"https://content.openalex.org/works/W7140078077.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Mariia":[0],"Fedorova,":[1],"Nikolay":[2],"Arefyev,":[3],"Maja":[4],"Buljan,":[5],"Jind\u0159ich":[6],"Helcl,":[7],"Stephan":[8],"Oepen,":[9],"Egil":[10],"R\u00f8nningstad,":[11],"Yves":[12],"Scherrer.":[13],"Proceedings":[14],"of":[15],"the":[16],"13th":[17],"Workshop":[18],"on":[19],"NLP":[20],"for":[21],"Similar":[22],"Languages,":[23],"Varieties":[24],"and":[25],"Dialects.":[26],"2026.":[27]},"counts_by_year":[],"updated_date":"2026-06-19T17:40:00.097472","created_date":"2026-02-18T00:00:00"}