{"id":"https://openalex.org/W4416035872","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.77","title":"Identifying Rare Languages in Common Crawl Data is a Needles-in-a-Haystack Problem","display_name":"Identifying Rare Languages in Common Crawl Data is a Needles-in-a-Haystack Problem","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4416035872","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.77"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.findings-emnlp.77","is_oa":false,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.77","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EMNLP 2025","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://inria.hal.science/hal-05361348","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5045054849","display_name":"Rasul Dent","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rasul Dent","raw_affiliation_strings":["ALMAnaCH - Automatic Language Modelling and ANAlysis & Computational Humanities (48 Rue Barrault, 75013 Paris - France)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ALMAnaCH - Automatic Language Modelling and ANAlysis & Computational Humanities (48 Rue Barrault, 75013 Paris - France)","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054913492","display_name":"Pedro Ortiz Su\u00e1rez","orcid":"https://orcid.org/0000-0003-0343-8852"},"institutions":[{"id":"https://openalex.org/I33256026","display_name":"German Research Centre for Artificial Intelligence","ror":"https://ror.org/01ayc5b57","country_code":"DE","type":"funder","lineage":["https://openalex.org/I33256026"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Pedro Ortiz Suarez","raw_affiliation_strings":["DFKI - Deutsches Forschungszentrum f\u00fcr K\u00fcnstliche Intelligenz GmbH = German Research Center for Artificial Intelligence (Stuhlsatzenhausweg 3Campus D3_2D-66123 Saarbruecken - Germany)","Common Crawl (United States)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DFKI - Deutsches Forschungszentrum f\u00fcr K\u00fcnstliche Intelligenz GmbH = German Research Center for Artificial Intelligence (Stuhlsatzenhausweg 3Campus D3_2D-66123 Saarbruecken - Germany)","institution_ids":["https://openalex.org/I33256026"]},{"raw_affiliation_string":"Common Crawl (United States)","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076012918","display_name":"Thibault Cl\u00e9rice","orcid":"https://orcid.org/0000-0003-1852-9204"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Thibault Cl\u00e9rice","raw_affiliation_strings":["ALMAnaCH - Automatic Language Modelling and ANAlysis & Computational Humanities (48 Rue Barrault, 75013 Paris - France)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ALMAnaCH - Automatic Language Modelling and ANAlysis & Computational Humanities (48 Rue Barrault, 75013 Paris - France)","institution_ids":[]}]},{"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":["ALMAnaCH - Automatic Language Modelling and ANAlysis & Computational Humanities (48 Rue Barrault, 75013 Paris - France)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ALMAnaCH - Automatic Language Modelling and ANAlysis & Computational Humanities (48 Rue Barrault, 75013 Paris - France)","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"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":0.3514518,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1460","last_page":"1473"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12090","display_name":"Language and cultural evolution","score":0.18549999594688416,"subfield":{"id":"https://openalex.org/subfields/3316","display_name":"Cultural Studies"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T12090","display_name":"Language and cultural evolution","score":0.18549999594688416,"subfield":{"id":"https://openalex.org/subfields/3316","display_name":"Cultural Studies"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12380","display_name":"Authorship Attribution and Profiling","score":0.05779999867081642,"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/T10265","display_name":"Multilingual Education and Policy","score":0.02969999983906746,"subfield":{"id":"https://openalex.org/subfields/3310","display_name":"Linguistics and Language"},"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/identification","display_name":"Identification (biology)","score":0.3050000071525574},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.30230000615119934},{"id":"https://openalex.org/keywords/rare-events","display_name":"Rare events","score":0.28600001335144043},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.2777999937534332}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.607200026512146},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.48069998621940613},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4212999939918518},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.3495999872684479},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.3050000071525574},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.30230000615119934},{"id":"https://openalex.org/C2777317252","wikidata":"https://www.wikidata.org/wiki/Q18393516","display_name":"Rare events","level":2,"score":0.28600001335144043},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.2777999937534332},{"id":"https://openalex.org/C2777855551","wikidata":"https://www.wikidata.org/wiki/Q12310021","display_name":"Subject (documents)","level":2,"score":0.2632000148296356},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.24639999866485596}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.18653/v1/2025.findings-emnlp.77","is_oa":false,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.77","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EMNLP 2025","raw_type":"proceedings-article"},{"id":"pmh:oai:HAL:hal-05361348v1","is_oa":true,"landing_page_url":"https://inria.hal.science/hal-05361348","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Findings of the Association for Computational Linguistics: EMNLP 2025, Nov 2025, Suzhou, China. pp.1460-1473, &#x27E8;10.18653/v1/2025.findings-emnlp.77&#x27E9;","raw_type":"Conference papers"}],"best_oa_location":{"id":"pmh:oai:HAL:hal-05361348v1","is_oa":true,"landing_page_url":"https://inria.hal.science/hal-05361348","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Findings of the Association for Computational Linguistics: EMNLP 2025, Nov 2025, Suzhou, China. pp.1460-1473, &#x27E8;10.18653/v1/2025.findings-emnlp.77&#x27E9;","raw_type":"Conference papers"},"sustainable_development_goals":[],"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"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"International":[0],"audience":[1]},"counts_by_year":[],"updated_date":"2026-06-22T08:00:12.763002","created_date":"2025-11-08T00:00:00"}
