{"id":"W4412944910","doi":"10.18653/v1/2025.acl-long.875","title":"Enhancing Text Editing for Grammatical Error Correction: Arabic as a Case Study","year":2025,"lang":"en","type":"article","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"York University; New York University Abu Dhabi","keywords":"Computer science; Arabic; Natural language processing; Artificial intelligence; Error analysis; Error detection and correction; Linguistics; Speech recognition; Algorithm; Mathematics; Philosophy","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00202993,0.001734361,0.0007171008,0.001224077,0.001009055,0.001506463,0.001645839,0.001506537,0.00301592],"category_scores_gemma":[0.01266918,0.0002278099,0.0006265159,0.001246605,0.0006737791,0.002075789,0.001121183,0.002000463,0.002312041],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008925034,"about_ca_system_score_gemma":0.001261986,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01086752,"about_ca_topic_score_gemma":0.0139361,"domain_scores_codex":[0.9984101,0.0006229157,0.0001298694,0.0003835669,0.0003504005,0.0001031905],"domain_scores_gemma":[0.9906969,0.004890081,0.0003917732,0.00141196,0.002287157,0.0003221867],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001045583,0.0009344461,0.01350333,0.001320006,0.0002276697,0.003999096,0.002344931,0.1675988,0.03425371,0.006118562,0.06840714,0.7002468],"study_design_scores_gemma":[0.0001251523,0.000470461,0.005158321,0.0001672717,0.0001428224,0.001901044,0.001293922,0.8071046,0.1017934,0.008167123,0.07352535,0.000150508],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6808166,0.004181614,0.2356692,0.005276644,0.001807782,0.000730561,0.005017434,0.04642406,0.02007619],"genre_scores_gemma":[0.7150146,0.001048005,0.2585824,0.001006509,0.0002663379,0.0001883703,0.007317267,0.002234476,0.01434194],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01086752,"threshold_uncertainty_score":0.02160853,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01571022280866232,"score_gpt":0.3346478321451965,"score_spread":0.3189376093365342,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}