{"id":"W4388477306","doi":"10.18280/ria.370524","title":"Assessing Semantic Similarity Measures and Proposing a WuP-Resnik Hybrid Metric for Enhanced Arabic Language Processing","year":2023,"lang":"en","type":"article","venue":"Revue d intelligence artificielle","topic":"Topic Modeling","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Arabic; Semantic similarity; Similarity (geometry); Metric (unit); Natural language processing; Computer science; Artificial intelligence; Linguistics; Philosophy; Engineering; Image (mathematics)","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"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":[0.004196886,0.001178428,0.001199628,0.008484272,0.0008542191,0.003023998,0.001233341,0.001410891,0.001538267],"category_scores_gemma":[0.01980176,0.0002684621,0.0009395947,0.005212631,0.001370298,0.005813691,0.001844091,0.001094896,0.001082386],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000938058,"about_ca_system_score_gemma":0.001274673,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001508617,"about_ca_topic_score_gemma":0.001648973,"domain_scores_codex":[0.9959269,0.001122552,0.0005022443,0.0005279178,0.00172024,0.0002001421],"domain_scores_gemma":[0.992947,0.002841261,0.0008897319,0.0008599076,0.002236818,0.0002252078],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0004256808,0.0002483479,0.007989005,0.0008380038,0.0002675758,0.0003636086,0.0009288745,0.05985392,0.05667905,0.05891406,0.005114704,0.8083772],"study_design_scores_gemma":[0.0000297909,0.0006718532,0.01031441,0.0001008114,0.0001431733,0.001045303,0.0007303847,0.8472794,0.0563639,0.07023849,0.01288705,0.000195453],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03758099,0.0007260932,0.957394,0.0002216898,0.0001125498,0.0001823513,0.0002189171,0.0005017337,0.003061655],"genre_scores_gemma":[0.3393525,0.0006237898,0.6571163,0.0000839423,0.0001400788,0.0002854361,0.0007093559,0.0001291668,0.001559498],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.008484272,"threshold_uncertainty_score":0.02219552,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07493175031527047,"score_gpt":0.3316384455456369,"score_spread":0.2567066952303664,"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."}}