{"id":"W2806318393","doi":"","title":"Sentences Embedding for Slot Filling via Convolutional Neural Networks.","year":2016,"lang":"en","type":"article","venue":"Theory and applications of categories","topic":"Topic Modeling","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"","funders":"","keywords":"Embedding; Convolutional neural network; Computer science; Artificial intelligence","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007183676,0.0006954548,0.0006451058,0.001212054,0.0004121187,0.0008464076,0.001183535,0.0008359983,0.008935159],"category_scores_gemma":[0.003945204,0.0003524564,0.0007655537,0.001304152,0.0003789557,0.003203648,0.001352931,0.001112942,0.003360778],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005808934,"about_ca_system_score_gemma":0.001061179,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002873693,"about_ca_topic_score_gemma":0.006850334,"domain_scores_codex":[0.9994612,0.0001494314,0.0000469275,0.0001615156,0.0001108399,0.00007005766],"domain_scores_gemma":[0.9989016,0.0005478309,0.00007910217,0.0002199207,0.0001936242,0.00005788474],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0005854142,0.0002823532,0.0013268,0.0005646453,0.0001004486,0.00016679,0.000419229,0.02554397,0.01173869,0.04241799,0.0666724,0.8501814],"study_design_scores_gemma":[0.00005724133,0.0001183798,0.0007316801,0.0001009587,0.00006961239,0.0001408347,0.0002079848,0.8435337,0.01065215,0.1166905,0.02766258,0.00003435491],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03896918,0.001956493,0.9358144,0.000893938,0.0005924063,0.0001893498,0.006179612,0.009627044,0.00577745],"genre_scores_gemma":[0.4486694,0.0009500799,0.5184415,0.0003364624,0.000404921,0.0003615342,0.01640264,0.0008301639,0.01360332],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.008935159,"threshold_uncertainty_score":0.02989107,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01461610296885664,"score_gpt":0.2577463917833841,"score_spread":0.2431302888145274,"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."}}