{"id":"https://openalex.org/W4416037680","doi":"https://doi.org/10.18653/v1/2025.arabicnlp-main.8","title":"ATHAR: A High-Quality and Diverse Dataset for Classical Arabic to English Translation","display_name":"ATHAR: A High-Quality and Diverse Dataset for Classical Arabic to English Translation","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4416037680","doi":"https://doi.org/10.18653/v1/2025.arabicnlp-main.8"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.arabicnlp-main.8","doi":"https://doi.org/10.18653/v1/2025.arabicnlp-main.8","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.arabicnlp-main.8","pdf_url":"https://aclanthology.org/2025.arabicnlp-main.8.pdf","source":{"id":"https://openalex.org/S7407085968","display_name":"Arabic Natural Language Processing Workshop (WANLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"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 Third Arabic Natural Language Processing Conference","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://aclanthology.org/2025.arabicnlp-main.8.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5110515094","display_name":"Mohammed S. Mohammed","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mohammed Sabry Mohammed","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Mohammed Khalil","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I42934936","display_name":"Dublin City University","ror":"https://ror.org/04a1a1e81","country_code":"IE","type":"education","lineage":["https://openalex.org/I42934936"]}],"countries":["IE"],"is_corresponding":false,"raw_author_name":"Mohammed Khalil","raw_affiliation_strings":["ADAPT/DCU , Dublin , Ireland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ADAPT/DCU , Dublin , Ireland","institution_ids":["https://openalex.org/I42934936"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"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":0.31865416,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"97","last_page":"106"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9839000105857849,"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":0.9839000105857849,"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/T10759","display_name":"Translation Studies and Practices","score":0.00860000029206276,"subfield":{"id":"https://openalex.org/subfields/1203","display_name":"Language and Linguistics"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.006099999882280827,"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/classical-arabic","display_name":"Classical Arabic","score":0.8420000076293945},{"id":"https://openalex.org/keywords/arabic-english-machine-translation","display_name":"Arabic-English machine translation","score":0.8640000224113464},{"id":"https://openalex.org/keywords/translation-dataset","display_name":"translation dataset","score":0.8309999704360962},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.6869999766349792},{"id":"https://openalex.org/keywords/translation-quality-assessment","display_name":"translation quality assessment","score":0.4000000059604645},{"id":"https://openalex.org/keywords/fine-tuning","display_name":"fine-tuning","score":0.6779999732971191},{"id":"https://openalex.org/keywords/pretraining","display_name":"pre-training","score":0.765999972820282},{"id":"https://openalex.org/keywords/arabic-philosophy","display_name":"Arabic philosophy","score":0.3799999952316284}],"concepts":[{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5838000178337097},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5755000114440918},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.554099977016449},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5415999889373779},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.45339998602867126},{"id":"https://openalex.org/C96455323","wikidata":"https://www.wikidata.org/wiki/Q13955","display_name":"Arabic","level":2,"score":0.3601999878883362},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.33000001311302185},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.2865000069141388},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.24690000712871552},{"id":"https://openalex.org/C155092808","wikidata":"https://www.wikidata.org/wiki/Q182557","display_name":"Computational linguistics","level":2,"score":0.23690000176429749}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.arabicnlp-main.8","doi":"https://doi.org/10.18653/v1/2025.arabicnlp-main.8","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.arabicnlp-main.8","pdf_url":"https://aclanthology.org/2025.arabicnlp-main.8.pdf","source":{"id":"https://openalex.org/S7407085968","display_name":"Arabic Natural Language Processing Workshop (WANLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"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 Third Arabic Natural Language Processing Conference","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.arabicnlp-main.8","doi":"https://doi.org/10.18653/v1/2025.arabicnlp-main.8","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.arabicnlp-main.8","pdf_url":"https://aclanthology.org/2025.arabicnlp-main.8.pdf","source":{"id":"https://openalex.org/S7407085968","display_name":"Arabic Natural Language Processing Workshop (WANLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"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 Third Arabic Natural Language Processing Conference","raw_type":"proceedings-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416037680.pdf","grobid_xml":"https://content.openalex.org/works/W4416037680.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7160246478","https://openalex.org/W4417223539","https://openalex.org/W4404401697","https://openalex.org/W6910909161","https://openalex.org/W7106682941","https://openalex.org/W4416383068","https://openalex.org/W4396764611","https://openalex.org/W7117541217","https://openalex.org/W4404823206","https://openalex.org/W7125184268"],"abstract_inverted_index":{"Classical":[0,60],"Arabic":[1,88],"represents":[2],"a":[3,18,54,95,120],"significant":[4],"era":[5],"that":[6,93,117],"encompasses":[7],"the":[8,22,34,71,80,107],"golden":[9],"age":[10],"of":[11,24,36,56,73,98,109],"Arab":[12],"culture,":[13,102],"philosophy,":[14],"and":[15,41,68,103],"scientific":[16],"literature.With":[17],"broad":[19],"consensus":[20],"on":[21],"importance":[23],"translating":[25],"these":[26],"literatures":[27],"to":[28,47,89],"enrich":[29],"knowledge":[30],"dissemination":[31],"across":[32],"communities,":[33],"advent":[35],"large":[37],"language":[38],"models":[39,131],"(LLMs)":[40],"translation":[42,57,75,91],"systems":[43],"offers":[44],"promising":[45],"tools":[46],"facilitate":[48],"this":[49,138],"goal.However,":[50],"we":[51,78,105],"have":[52],"identified":[53],"scarcity":[55],"datasets":[58,124],"in":[59,66,125],"Arabic,":[61],"which":[62,83],"are":[63],"often":[64],"limited":[65],"scope":[67],"topics,":[69],"hindering":[70],"development":[72],"high-quality":[74,86],"systems.In":[76],"response,":[77],"present":[79],"ATHAR":[81],"dataset,":[82],"comprises":[84],"66,000":[85],"classical":[87],"English":[90],"samples":[92],"cover":[94],"wide":[96],"array":[97],"topics":[99],"including":[100],"science,":[101],"philosophy.Furthermore,":[104],"assess":[106],"performance":[108],"current":[110,126],"state-of-the-art":[111],"LLMs":[112],"under":[113],"various":[114],"settings,":[115],"concluding":[116],"there":[118],"is":[119],"need":[121],"for":[122],"such":[123],"systems.Our":[127],"findings":[128],"highlight":[129],"how":[130],"can":[132],"benefit":[133],"from":[134],"fine-tuning":[135],"or":[136],"incorporating":[137],"dataset":[139],"into":[140],"their":[141],"pretraining":[142],"pipelines.":[143]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2025-11-08T00:00:00"}
