{"id":"W4389518395","doi":"10.18653/v1/2023.arabicnlp-1.83","title":"WojoodNER 2023: The First Arabic Named Entity Recognition Shared Task","year":2023,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Arabic; Named-entity recognition; Computer science; Task (project management); Natural language processing; Focus (optics); Artificial intelligence; Linguistics; Engineering","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":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0003414409,0.00008035813,0.00007476743,0.00006595274,0.0001927665,0.0002032785,0.0006907757,0.00004185467,0.0003018313],"category_scores_gemma":[0.00007354918,0.00005479511,0.00005373802,0.0005524808,0.00001869486,0.0003720509,0.0003032982,0.0001092671,0.002477669],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002555281,"about_ca_system_score_gemma":0.00002574527,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001252367,"about_ca_topic_score_gemma":0.0002152559,"domain_scores_codex":[0.9990428,0.00003369254,0.0001523703,0.0003067496,0.0002314218,0.0002329379],"domain_scores_gemma":[0.9992425,0.00009155176,0.00003673668,0.0005322396,0.0000532521,0.0000436533],"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":[0.00001447967,0.0001791325,0.004961593,0.0001118396,0.000130363,0.0000926653,0.006440771,0.002252174,0.001225064,0.04830605,0.4253809,0.510905],"study_design_scores_gemma":[0.0003827492,0.00002810524,0.0115719,0.00003869049,0.000008769605,0.000009597021,0.00009952846,0.8986444,0.0005562949,0.03404818,0.05430586,0.0003059411],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.145946,0.00008623477,0.7599732,0.04286867,0.002958975,0.000683149,0.00001810437,0.002089108,0.04537664],"genre_scores_gemma":[0.9781111,0.00003253355,0.0100488,0.002209544,0.0002304136,0.00008230612,0.00002338433,0.00001150814,0.009250421],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8963922,"threshold_uncertainty_score":0.998299,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04759203722951118,"score_gpt":0.2443203422839928,"score_spread":0.1967283050544816,"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."}}