{"id":"W6976619488","doi":"10.60692/6pxh0-f5314","title":"On the Role of Orthographic Variations in Building Multidialectal Arabic Word Embeddings","year":2021,"lang":"en","type":"article","venue":"Greater South Information System","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Sherbrooke","funders":"","keywords":"Word embedding; Lexicon; Word (group theory); Orthographic projection; Embedding; Canonical correlation; Arabic; Space (punctuation)","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008696023,0.0008705097,0.0003302188,0.000973855,0.0004841261,0.0009422411,0.0005001618,0.0004107806,0.002142851],"category_scores_gemma":[0.003151658,0.0002618511,0.0005586375,0.001005527,0.0004877592,0.002264234,0.001185811,0.0009350419,0.001626143],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002522865,"about_ca_system_score_gemma":0.0007275681,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003584418,"about_ca_topic_score_gemma":0.009849024,"domain_scores_codex":[0.9992095,0.0003192662,0.00005381506,0.0002846352,0.00008756798,0.00004514613],"domain_scores_gemma":[0.9986343,0.0006491215,0.0001000762,0.000266822,0.0002978239,0.00005179887],"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":[0.0002146709,0.000165271,0.006811653,0.000208271,0.0001306902,0.0001689931,0.0005910241,0.02873653,0.0350293,0.008674745,0.004744015,0.9145249],"study_design_scores_gemma":[0.00002964551,0.0002564637,0.009900419,0.00007896155,0.0001142052,0.0004528175,0.000869784,0.9214356,0.03940121,0.01566638,0.01172865,0.0000658514],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1715554,0.001137823,0.818618,0.000349587,0.0001631247,0.0001065283,0.0004110305,0.002437688,0.005220752],"genre_scores_gemma":[0.6005219,0.0007765254,0.3899054,0.000166644,0.0000739419,0.0001102769,0.002145681,0.0004499075,0.005849707],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003584418,"threshold_uncertainty_score":0.007168531,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01208779424678677,"score_gpt":0.2160990264817,"score_spread":0.2040112322349132,"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."}}