{"id":"W3150524533","doi":"10.1007/978-3-030-73197-7_5","title":"Generating Contextually Coherent Responses by Learning Structured Vectorized Semantics","year":2021,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Topic Modeling","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Windsor","funders":"","keywords":"Semantics (computer science); Computer science; Linguistics; Psychology; Natural language processing; Communication; Programming language; Philosophy","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":[0.001477551,0.001386742,0.001013668,0.0009061029,0.000415367,0.001229062,0.001482205,0.001589597,0.00767057],"category_scores_gemma":[0.00743196,0.0005233068,0.001132557,0.0009294116,0.0005912419,0.002566375,0.002153585,0.002070356,0.003702541],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004361678,"about_ca_system_score_gemma":0.0008793151,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001003961,"about_ca_topic_score_gemma":0.001831402,"domain_scores_codex":[0.9981622,0.0007846279,0.00007333061,0.000553149,0.0002757647,0.0001509108],"domain_scores_gemma":[0.9968677,0.002186531,0.0001351656,0.0002783751,0.0004241249,0.0001081009],"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":[0.001783752,0.0005249321,0.001496499,0.0005567012,0.0001901622,0.000333461,0.0009003653,0.03444505,0.07561912,0.02481015,0.01832214,0.8410177],"study_design_scores_gemma":[0.000142643,0.000387026,0.0007758105,0.00006706979,0.0001110721,0.0002015214,0.0005779835,0.8974538,0.02508498,0.06852352,0.00660967,0.00006483484],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02866076,0.000266087,0.9627298,0.0003478988,0.0001921595,0.0001494855,0.0004193332,0.004984164,0.002250404],"genre_scores_gemma":[0.4251554,0.0003995754,0.563366,0.0004082101,0.0003079096,0.0004260662,0.002816197,0.0008896241,0.006231062],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00767057,"threshold_uncertainty_score":0.02566063,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02190177333141051,"score_gpt":0.2550366462127279,"score_spread":0.2331348728813174,"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."}}