{"id":"W2775747321","doi":"","title":"WiNER: A Wikipedia Annotated Corpus for Named Entity Recognition","year":2017,"lang":"en","type":"article","venue":"International Joint Conference on Natural Language Processing","topic":"Topic Modeling","field":"Computer Science","cited_by":38,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"","keywords":"Computer science; Natural language processing; Information retrieval; Artificial intelligence; Quality (philosophy); Named-entity recognition; Simple (philosophy); Training set; Range (aeronautics); Task (project management)","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":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0002216499,0.0001662159,0.0001638252,0.000132749,0.0003315587,0.001215751,0.001099408,0.00007084821,0.0000272404],"category_scores_gemma":[0.0006368777,0.0001490651,0.00007789567,0.00004713139,0.00005449266,0.001249085,0.0001989591,0.0002501852,0.00002677619],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000834678,"about_ca_system_score_gemma":0.0001215498,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008452532,"about_ca_topic_score_gemma":0.00004247102,"domain_scores_codex":[0.9986302,0.00002212801,0.0002683507,0.0004632001,0.0003778611,0.0002383076],"domain_scores_gemma":[0.9985484,0.00004202417,0.0003729384,0.0003855807,0.0005849234,0.00006607336],"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":[0.00004843885,0.00004998727,0.000138822,0.00003848994,0.00002342939,0.00004119777,0.0008704222,0.00001046587,0.01578257,0.006829258,0.0001037293,0.9760632],"study_design_scores_gemma":[0.001118214,0.00005823079,0.001565109,0.0004413766,0.00001102854,0.00004136666,0.0001175195,0.9737205,0.0124094,0.009639973,0.0004942761,0.000383012],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.359935,0.0006924808,0.6114752,0.01139822,0.006048809,0.0006839986,0.00007335595,0.0005423714,0.009150531],"genre_scores_gemma":[0.9565787,0.000009600278,0.04173307,0.0004337488,0.0003500242,0.00003644488,0.00005518902,0.00001023416,0.0007929472],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9756802,"threshold_uncertainty_score":0.9998211,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06018724801345868,"score_gpt":0.3217091971620433,"score_spread":0.2615219491485846,"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."}}