{"id":"W2084189120","doi":"10.1016/j.mcm.2006.06.001","title":"A formal approach to subgrammar extraction for NLP","year":2006,"lang":"en","type":"article","venue":"Mathematical and Computer Modelling","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":false,"ca_institutions":"Dalhousie University","funders":"","keywords":"Computer science; Parsing; Set (abstract data type); Context (archaeology); Artificial intelligence; Rule-based machine translation; Context-free grammar; Grammar; Algorithm; Natural language processing; Theoretical computer science; Programming language; 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":[0.005517803,0.0009224944,0.00111664,0.00364812,0.002195034,0.007351079,0.004466739,0.002127497,0.009497858],"category_scores_gemma":[0.01167327,0.002155145,0.004162432,0.002693453,0.006054445,0.01068887,0.005151621,0.005309102,0.003665336],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002197262,"about_ca_system_score_gemma":0.00287059,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003554887,"about_ca_topic_score_gemma":0.006136612,"domain_scores_codex":[0.9949548,0.001539816,0.0008373258,0.0007958692,0.001597414,0.0002747844],"domain_scores_gemma":[0.9925222,0.00344105,0.0004203488,0.001971402,0.001438742,0.0002062273],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00002664192,0.00005535099,0.0001749862,0.0003002062,0.00005222535,0.0002323819,0.0004653838,0.007714798,0.002535016,0.9360783,0.003486734,0.04887809],"study_design_scores_gemma":[0.00002392574,0.0000288085,0.0001364131,0.0001420905,0.00006950019,0.000355333,0.0001474398,0.07483923,0.004957521,0.873808,0.04542984,0.00006189522],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0003962436,0.00009951834,0.9972453,0.0002904157,0.00003885879,0.0000537477,0.0001093741,0.0005701602,0.001196445],"genre_scores_gemma":[0.02811798,0.0003177628,0.9682943,0.0002193426,0.0001482135,0.0002133743,0.0005150869,0.0003230018,0.001851017],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.009497858,"threshold_uncertainty_score":0.03177345,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0229304784422572,"score_gpt":0.2505988035083456,"score_spread":0.2276683250660884,"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."}}