{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001210748,0.0002187568,0.0002965199,0.0003796269,0.0004802652,0.0007838222,0.0005985672,0.00006892982,0.00000454661],"category_scores_gemma":[0.0006337192,0.0002132934,0.00009032772,0.00130245,0.00007176974,0.0008984446,0.0002502009,0.0002060355,0.00003699018],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006125645,"about_ca_system_score_gemma":0.0001041928,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002669872,"about_ca_topic_score_gemma":0.00001006228,"domain_scores_codex":[0.9977773,0.00007790214,0.000488445,0.0007871581,0.0002981529,0.0005710215],"domain_scores_gemma":[0.9986451,0.0003234551,0.0001685449,0.0005732445,0.0001744985,0.000115201],"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":[0.000007692494,0.00006584848,0.0001392313,0.0005423964,0.00001741697,0.00003329501,0.006251588,0.02563522,0.05489,0.001550463,0.00007122884,0.9107956],"study_design_scores_gemma":[0.00004682324,0.00003704313,0.00004878552,0.0002011885,0.00001284725,0.00002109311,0.001016298,0.7914833,0.2038869,0.002882438,0.0001447365,0.0002184966],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2418272,0.0008976491,0.7554228,0.0006271181,0.0002119918,0.0004076327,0.000001407328,0.0003553442,0.000248822],"genre_scores_gemma":[0.965829,0.00004391019,0.03351677,0.0001072699,0.0001112912,0.0000579554,0.000004046451,0.00002458068,0.0003051383],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9105771,"threshold_uncertainty_score":0.8697852,"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."}}