{"id":"W4385571292","doi":"10.18653/v1/2023.law-1.22","title":"Unified Syntactic Annotation of English in the CGEL Framework","year":2023,"lang":"en","type":"article","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Humber Polytechnic","funders":"National Science Foundation","keywords":"Treebank; Computer science; Annotation; Natural language processing; Artificial intelligence; Formalism (music); Grammar; Syntax; English grammar; Linguistics","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":[0.003394399,0.0008253279,0.0007740706,0.003922056,0.001562852,0.003892391,0.001757871,0.0009601544,0.009516178],"category_scores_gemma":[0.0068705,0.0007306899,0.0007757114,0.003823563,0.002329966,0.007885438,0.003044273,0.001825938,0.002689715],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002018649,"about_ca_system_score_gemma":0.002379975,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007975573,"about_ca_topic_score_gemma":0.01082787,"domain_scores_codex":[0.9980848,0.0007442356,0.0001648787,0.0005150579,0.0003415274,0.0001495841],"domain_scores_gemma":[0.99644,0.001218423,0.0002116607,0.001038635,0.0009916128,0.000099638],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001300802,0.00007078505,0.0008447585,0.0003809814,0.00003006188,0.0005823005,0.003642403,0.00600674,0.008234611,0.8822981,0.01675797,0.08102119],"study_design_scores_gemma":[0.00007637211,0.00006392159,0.002371619,0.0004583244,0.0001153987,0.0006013967,0.001813552,0.07235973,0.02433693,0.4366951,0.4609456,0.0001621309],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01923466,0.0003765727,0.939595,0.001266591,0.0002682552,0.0001637489,0.003005194,0.005747327,0.0303426],"genre_scores_gemma":[0.2235006,0.0004504575,0.7561174,0.0007103027,0.0001609022,0.0003048148,0.006492095,0.002772714,0.009490707],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.009516178,"threshold_uncertainty_score":0.03183478,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0166528682578255,"score_gpt":0.2916388996318318,"score_spread":0.2749860313740063,"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."}}