{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002338363,0.0001249462,0.0001585036,0.00007154116,0.0001263548,0.0002702042,0.0002986878,0.00005942974,4.796515e-7],"category_scores_gemma":[0.000003439289,0.00009915954,0.00004896954,0.0001212945,0.00001469436,0.0004126635,0.0001600727,0.0000856652,0.000003717924],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001448325,"about_ca_system_score_gemma":0.000007879678,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007601557,"about_ca_topic_score_gemma":2.054911e-7,"domain_scores_codex":[0.9990673,0.0000106643,0.000208618,0.0002998206,0.0001446798,0.000268931],"domain_scores_gemma":[0.9995685,0.00007860032,0.00004101431,0.0001902385,0.00005522352,0.00006641071],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00000491013,0.00009018531,0.000001010445,0.0001195986,0.00000305712,0.000001039237,0.0001937628,0.006675617,0.00007786076,0.9590076,0.0001733564,0.033652],"study_design_scores_gemma":[0.00006329325,0.00003262253,5.421638e-7,0.00002083429,0.00000281715,0.00002305704,0.000001579439,0.6235425,0.0005393674,0.375486,0.0001961088,0.00009126058],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.002131663,0.0001401775,0.9965013,0.0001644711,0.000037733,0.0002880554,6.863326e-7,0.0003558195,0.0003800826],"genre_scores_gemma":[0.155606,7.210188e-7,0.8439952,0.0001299502,0.0001282186,0.00004954158,0.000002225213,0.000008092585,0.00008003991],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.6168669,"threshold_uncertainty_score":0.4043609,"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."}}