{"id":"W98931015","doi":"10.1038/npre.2008.2310.1","title":"Performance of the Charniak-Lease parser on biological text using different training corpora","year":2008,"lang":"en","type":"preprint","venue":"Nature Precedings","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Nature Conservancy of Canada; Carleton University; University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; Universities Space Research Association; Carleton University","keywords":"Computer science; Natural language processing; Parsing; Artificial intelligence; Text corpus","routes":{"ca_aff":true,"ca_fund":true,"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":[0.007472343,0.001051887,0.0009540997,0.001754767,0.001117615,0.002273909,0.001323283,0.00179646,0.005002057],"category_scores_gemma":[0.02012055,0.0008096367,0.0007483177,0.002008395,0.001045245,0.00339773,0.001568909,0.001573825,0.002971184],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001464793,"about_ca_system_score_gemma":0.001357249,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009861857,"about_ca_topic_score_gemma":0.01213294,"domain_scores_codex":[0.9964006,0.00149958,0.0003147502,0.001019974,0.0005551227,0.0002099213],"domain_scores_gemma":[0.9771652,0.01776782,0.0004623877,0.001911284,0.002403001,0.0002903149],"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":[0.006693775,0.001996439,0.03154939,0.002732213,0.0009481391,0.002159867,0.004252964,0.1208425,0.2339993,0.007335128,0.08209561,0.5053946],"study_design_scores_gemma":[0.0007728357,0.00127847,0.04311818,0.0002827056,0.0004664191,0.000851666,0.001893013,0.591645,0.3270745,0.00593813,0.02631303,0.0003661812],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8951697,0.001063809,0.04212957,0.001109468,0.0003723481,0.000383857,0.009919724,0.03474252,0.01510906],"genre_scores_gemma":[0.8704231,0.0003321347,0.08761029,0.0003575254,0.00005746493,0.0003516061,0.03190295,0.002861029,0.006103789],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.009861857,"threshold_uncertainty_score":0.03951794,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05159216876529966,"score_gpt":0.2861195937781131,"score_spread":0.2345274250128135,"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."}}