{"id":"https://openalex.org/W4412888009","doi":"https://doi.org/10.18653/v1/2025.findings-acl.842","title":"A Large and Balanced Corpus for Fine-grained Arabic Readability Assessment","display_name":"A Large and Balanced Corpus for Fine-grained Arabic Readability Assessment","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412888009","doi":"https://doi.org/10.18653/v1/2025.findings-acl.842"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.findings-acl.842","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.842","pdf_url":"https://aclanthology.org/2025.findings-acl.842.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.842.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5039496741","display_name":"Khalid N. Elmadani","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Khalid Elmadani","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084517393","display_name":"Nizar Habash","orcid":"https://orcid.org/0000-0002-1831-3457"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nizar Habash","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5013885994","display_name":"Hanada Taha","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hanada Taha","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":1.673,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.83330056,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"16376","last_page":"16400"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13629","display_name":"Text Readability and Simplification","score":0.9941999912261963,"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/T13629","display_name":"Text Readability and Simplification","score":0.9941999912261963,"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":0.9542999863624573,"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/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.927299976348877,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/readability","display_name":"Readability","score":0.9163486957550049},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7524228096008301},{"id":"https://openalex.org/keywords/arabic","display_name":"Arabic","score":0.7445852756500244},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6183551549911499},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5026893615722656},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.24808436632156372},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.17918860912322998}],"concepts":[{"id":"https://openalex.org/C2778143727","wikidata":"https://www.wikidata.org/wiki/Q1820650","display_name":"Readability","level":2,"score":0.9163486957550049},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7524228096008301},{"id":"https://openalex.org/C96455323","wikidata":"https://www.wikidata.org/wiki/Q13955","display_name":"Arabic","level":2,"score":0.7445852756500244},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6183551549911499},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5026893615722656},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.24808436632156372},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.17918860912322998},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.findings-acl.842","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.842","pdf_url":"https://aclanthology.org/2025.findings-acl.842.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"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.findings-acl.842","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.842","pdf_url":"https://aclanthology.org/2025.findings-acl.842.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":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320313203","display_name":"New York University Abu Dhabi","ror":"https://ror.org/00e5k0821"},{"id":"https://openalex.org/F4320319918","display_name":"York University","ror":"https://ror.org/05fq50484"},{"id":"https://openalex.org/F4320325295","display_name":"Zayed University","ror":"https://ror.org/03snqfa66"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412888009.pdf","grobid_xml":"https://content.openalex.org/works/W4412888009.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W1964661231","https://openalex.org/W4254960163","https://openalex.org/W3110264473","https://openalex.org/W2999103397","https://openalex.org/W2370831213","https://openalex.org/W4315704968","https://openalex.org/W3204019825"],"abstract_inverted_index":{"This":[0],"paper":[1],"introduces":[2],"the":[3,87,105],"Balanced":[4],"Arabic":[5,16,54,110],"Readability":[6],"Evaluation":[7],"Corpus":[8],"(BAREC),":[9],"1":[10],"a":[11,49,63,80,99],"large-scale,":[12],"fine-grained":[13],"dataset":[14],"for":[15,52],"readability":[17,32,92,111],"assessment.BAREC":[18],"consists":[19],"of":[20,66,83,101],"69,441":[21],"sentences":[22],"spanning":[23],"1+":[24],"million":[25],"words,":[26],"carefully":[27],"curated":[28],"to":[29,36],"cover":[30],"19":[31],"levels,":[33,97],"from":[34],"kindergarten":[35],"postgraduate":[37],"comprehension.The":[38],"corpus":[39,57],"balances":[40],"genre":[41],"diversity,":[42],"topical":[43],"coverage,":[44],"and":[45,107,121,133],"target":[46],"audiences,":[47],"offering":[48],"comprehensive":[50],"resource":[51],"evaluating":[53],"text":[55],"complexity.The":[56],"was":[58],"fully":[59],"manually":[60],"annotated":[61],"by":[62,73],"large":[64],"team":[65],"annotators.The":[67],"average":[68],"pairwise":[69],"inter-annotator":[70],"agreement,":[71],"measured":[72],"Quadratic":[74],"Weighted":[75],"Kappa,":[76],"is":[77],"81.8%,":[78],"reflecting":[79],"high":[81],"level":[82],"substantial":[84],"agreement.Beyond":[85],"presenting":[86],"corpus,":[88],"we":[89,123],"benchmark":[90,134],"automatic":[91],"assessment":[93],"across":[94,116],"different":[95],"granularity":[96],"comparing":[98],"range":[100],"techniques.Our":[102],"results":[103],"highlight":[104],"challenges":[106],"opportunities":[108],"in":[109],"modeling,":[112],"demonstrating":[113],"competitive":[114],"performance":[115],"various":[117],"methods.To":[118],"support":[119],"research":[120],"education,":[122],"make":[124],"BAREC":[125],"openly":[126],"available,":[127],"along":[128],"with":[129],"detailed":[130],"annotation":[131],"guidelines":[132],"results.":[135]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}