{"id":"W2909731903","doi":"10.1109/smc.2018.00013","title":"A Cognitive Machine Learning System for Phrases Composition and Semantic Comprehension","year":2018,"lang":"en","type":"article","venue":"","topic":"Cognitive Computing and Networks","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Calgary","funders":"","keywords":"Computer science; Natural language processing; Artificial intelligence; Phrase; Semantics (computer science); Sentence; Comprehension; Computational linguistics; Unsupervised learning; Computational semantics; Cognition; Operational semantics; Programming language; Psychology","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":[0.0001862085,0.0001136373,0.0001488386,0.00006862358,0.0004068712,0.0001216905,0.0001135785,0.00003658587,0.000003454364],"category_scores_gemma":[0.00002493131,0.00009971961,0.00003576219,0.000147002,0.00007073223,0.0001186218,0.0001843453,0.00008234211,0.00002026589],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000133867,"about_ca_system_score_gemma":0.00001010154,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002002479,"about_ca_topic_score_gemma":0.000008604177,"domain_scores_codex":[0.9991465,0.00008978619,0.000136091,0.0003304404,0.00009962269,0.0001975566],"domain_scores_gemma":[0.9989472,0.0005883524,0.0000646187,0.0000902385,0.0002462133,0.00006338912],"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":[0.0005745144,0.0003669891,0.007299137,0.0006843155,0.000254723,0.0000534182,0.004192717,0.0002285571,0.01709176,0.03835956,0.001675979,0.9292184],"study_design_scores_gemma":[0.0008422203,0.0004088707,0.0009238119,0.0004184415,0.00002144017,0.00007855184,0.0001148135,0.9912795,0.005382926,0.0001297462,0.0002345941,0.0001650468],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1564382,0.0001869733,0.841371,0.00009233478,0.0001990941,0.0002121783,0.000002049876,0.0003332618,0.001164952],"genre_scores_gemma":[0.9906744,0.000006733386,0.008846963,0.0001844921,0.0001784908,0.000008689689,0.00001287217,0.000007850337,0.00007947655],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.991051,"threshold_uncertainty_score":0.4066448,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02205152266344557,"score_gpt":0.2629766444623343,"score_spread":0.2409251217988888,"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."}}