{"id":"https://openalex.org/W4404401697","doi":"https://doi.org/10.48550/arxiv.2411.06402","title":"Fineweb-Edu-Ar: Machine-translated Corpus to Support Arabic Small Language Models","display_name":"Fineweb-Edu-Ar: Machine-translated Corpus to Support Arabic Small Language Models","publication_year":2024,"publication_date":"2024-11-10","ids":{"openalex":"https://openalex.org/W4404401697","doi":"https://doi.org/10.48550/arxiv.2411.06402"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2411.06402","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2411.06402","pdf_url":"https://arxiv.org/pdf/2411.06402","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2411.06402","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5093876169","display_name":"Sultan Alrashed","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I71920554","display_name":"King Abdullah University of Science and Technology","ror":"https://ror.org/01q3tbs38","country_code":"SA","type":"education","lineage":["https://openalex.org/I71920554"]}],"countries":["SA"],"is_corresponding":false,"raw_author_name":"Alrashed, Sultan","raw_affiliation_strings":["King Abdullah University of Science & Technology (KAUST)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"King Abdullah University of Science & Technology (KAUST)","institution_ids":["https://openalex.org/I71920554"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005741742","display_name":"Dmitrii Khizbullin","orcid":"https://orcid.org/0009-0007-2333-8206","observed_orcids":["https://orcid.org/0009-0007-2333-8206"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Khizbullin, Dmitrii","raw_affiliation_strings":["Saudi Data & Artificial Intelligence Authority"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Saudi Data & Artificial Intelligence Authority","institution_ids":[]}]},{"author_position":"last","author":{"id":null,"display_name":"Pugh, David R.","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I71920554","display_name":"King Abdullah University of Science and Technology","ror":"https://ror.org/01q3tbs38","country_code":"SA","type":"education","lineage":["https://openalex.org/I71920554"]}],"countries":["SA"],"is_corresponding":false,"raw_author_name":"Pugh, David R.","raw_affiliation_strings":["KAUST"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"KAUST","institution_ids":["https://openalex.org/I71920554"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"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":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.951200008392334,"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":0.951200008392334,"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":0.046300001442432404,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.00039999998989515007,"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/machine-translation","display_name":"machine translation","score":0.6809999942779541},{"id":"https://openalex.org/keywords/arabic-language-models","display_name":"Arabic language models","score":0.7599999904632568},{"id":"https://openalex.org/keywords/small-language-models","display_name":"small language models","score":0.8460000157356262},{"id":"https://openalex.org/keywords/multilingual-large-language-models","display_name":"multilingual large language models","score":0.8050000071525574},{"id":"https://openalex.org/keywords/synthetic-training-data","display_name":"synthetic training data","score":0.7379999756813049},{"id":"https://openalex.org/keywords/low-resource-languages","display_name":"low-resource languages","score":0.734000027179718}],"concepts":[{"id":"https://openalex.org/C96455323","wikidata":"https://www.wikidata.org/wiki/Q13955","display_name":"Arabic","level":2,"score":0.7786864638328552},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6605994701385498},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.639487624168396},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5254756212234497},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.47528377175331116},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.08522734045982361}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2411.06402","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2411.06402","pdf_url":"https://arxiv.org/pdf/2411.06402","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2411.06402","doi":"https://doi.org/10.48550/arxiv.2411.06402","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2411.06402","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2411.06402","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2411.06402","pdf_url":"https://arxiv.org/pdf/2411.06402","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320322320","display_name":"King Abdullah University of Science and Technology","ror":"https://ror.org/01q3tbs38"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4404401697.pdf","grobid_xml":"https://content.openalex.org/works/W4404401697.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4407764097","https://openalex.org/W4404354120","https://openalex.org/W4416037835","https://openalex.org/W4414900996","https://openalex.org/W7159978671","https://openalex.org/W7168079514","https://openalex.org/W6910909161","https://openalex.org/W4389518387","https://openalex.org/W7106120916","https://openalex.org/W7166860356"],"abstract_inverted_index":{"As":[0],"large":[1],"language":[2],"models":[3],"(LLMs)":[4],"grow":[5],"and":[6,25],"develop,":[7],"so":[8],"do":[9],"their":[10],"data":[11,28],"demands.":[12],"This":[13,62],"is":[14,46,54,85],"especially":[15],"true":[16],"for":[17],"multilingual":[18],"LLMs,":[19],"where":[20,50],"the":[21,70,79,86],"scarcity":[22],"of":[23,35,69,81,98,101],"high-quality":[24,51],"readily":[26],"available":[27,89],"online":[29],"has":[30],"led":[31],"to":[32,56],"a":[33,57,66],"multitude":[34],"synthetic":[36],"dataset":[37,75,92],"generation":[38],"approaches.":[39],"A":[40],"key":[41],"technique":[42],"in":[43],"this":[44],"space":[45],"machine":[47],"translation":[48],"(MT),":[49],"English":[52],"text":[53],"adapted":[55],"target,":[58],"comparatively":[59],"low-resource":[60],"language.":[61],"report":[63],"introduces":[64],"FineWeb-Edu-Ar,":[65],"machine-translated":[67,90],"version":[68],"exceedingly":[71],"popular":[72],"(deduplicated)":[73],"FineWeb-Edu":[74],"from":[76],"HuggingFace.":[77],"To":[78],"best":[80],"our":[82],"knowledge,":[83],"FineWeb-Edu-Ar":[84],"largest":[87],"publicly":[88],"Arabic":[91],"out":[93],"there,":[94],"with":[95],"its":[96],"size":[97],"202B":[99],"tokens":[100],"an":[102],"Arabic-trained":[103],"tokenizer.":[104]},"counts_by_year":[],"updated_date":"2026-10-13T10:08:12.033832","created_date":"2024-11-15T00:00:00"}
