{"id":"W4402671426","doi":"10.18653/v1/2024.arabicnlp-1.101","title":"WojoodNER 2024: The Second Arabic Named Entity Recognition Shared Task","year":2024,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":false,"ca_institutions":"","funders":"Alliance de recherche numérique du Canada; Social Sciences and Humanities Research Council of Canada; Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs; Birzeit University","keywords":"Computer science; Arabic; Task (project management); Natural language processing; Artificial intelligence; Entity linking; Named-entity recognition; Speech recognition; Linguistics; Engineering; Knowledge base","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":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.000295751,0.00008557056,0.00007004043,0.00005769523,0.00008437052,0.0005471291,0.0005024109,0.00004335563,0.003570662],"category_scores_gemma":[0.00002321917,0.00005504011,0.00006227168,0.0002625728,0.00001807666,0.000584784,0.0001800686,0.0001781144,0.001051545],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003256344,"about_ca_system_score_gemma":0.00005190112,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002976841,"about_ca_topic_score_gemma":0.0001102517,"domain_scores_codex":[0.9990851,0.00004607954,0.0001521543,0.0003545812,0.0001815337,0.0001805995],"domain_scores_gemma":[0.9993899,0.00008328207,0.00001754876,0.0004257415,0.00003822533,0.00004522918],"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":[0.000004678326,0.00007343054,0.0001816981,0.0002003618,0.0001296088,0.00008783877,0.004191315,0.00008800079,0.004074934,0.09584517,0.184765,0.710358],"study_design_scores_gemma":[0.000159333,0.0000260815,0.0004237685,0.00006837673,0.00001223137,0.00003791536,0.00006358245,0.7538739,0.00204433,0.07650585,0.1665117,0.0002728158],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04967308,0.000538566,0.8631359,0.006476551,0.00335203,0.0002591639,0.00001527121,0.0006128314,0.07593656],"genre_scores_gemma":[0.9262348,0.00001165155,0.01795231,0.001579905,0.000291179,0.00003955173,0.000007848374,0.00001056547,0.05387222],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8765617,"threshold_uncertainty_score":0.9997262,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0318173123631445,"score_gpt":0.2448831006226526,"score_spread":0.2130657882595081,"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."}}