{"id":"W2114914460","doi":"10.1109/ccece.1993.332374","title":"Using random graphs in learning past tenses","year":2002,"lang":"en","type":"article","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Redundancy (engineering); Artificial intelligence; Probabilistic logic; Exploit; Natural language processing; Connectionism; Knowledge base; Process (computing); Machine learning; Artificial neural network; Programming language","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":[0.00192308,0.0007133105,0.0005936807,0.003058757,0.0006862817,0.00129006,0.001234647,0.0009536045,0.002400847],"category_scores_gemma":[0.01054875,0.0005739845,0.0008950061,0.001781403,0.001277709,0.004699538,0.0008787279,0.00107932,0.0007226976],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009037033,"about_ca_system_score_gemma":0.0006406509,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003737683,"about_ca_topic_score_gemma":0.00663572,"domain_scores_codex":[0.9989181,0.000480374,0.00006322016,0.0003203721,0.0001631925,0.00005485543],"domain_scores_gemma":[0.9927405,0.005723899,0.0004800736,0.0005805026,0.0003487082,0.0001262843],"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":[0.0003681719,0.0002616041,0.008197405,0.0003875342,0.0002318572,0.0003046331,0.0004430024,0.3840134,0.003979417,0.0905817,0.006020825,0.5052104],"study_design_scores_gemma":[0.00003158212,0.00006915446,0.001220587,0.00005114121,0.00004374957,0.0001162225,0.00006401253,0.8302155,0.002060225,0.1606534,0.005423329,0.00005097623],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04678987,0.00102226,0.9444831,0.0006377367,0.0000855616,0.00009459144,0.000453301,0.00196873,0.004464897],"genre_scores_gemma":[0.6422368,0.001294208,0.3497185,0.0003522762,0.0001534727,0.0002221955,0.001896357,0.0003178147,0.003808363],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003737683,"threshold_uncertainty_score":0.01017034,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03135444347380327,"score_gpt":0.2731964397984948,"score_spread":0.2418419963246915,"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."}}