{"id":"W3199446243","doi":"10.1109/tnnls.2021.3112045","title":"Combining Knowledge Graph and Word Embeddings for Spherical Topic Modeling","year":2021,"lang":"en","type":"article","venue":"IEEE Transactions on Neural Networks and Learning Systems","topic":"Topic Modeling","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Interpretability; Hypersphere; Artificial intelligence; Natural language processing; Topic model; Leverage (statistics); Discriminative model; Word (group theory); Probabilistic logic; Graph; Set (abstract data type); Machine learning; Theoretical computer science; Mathematics","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0002572329,0.0001641488,0.0002552793,0.00005412029,0.0005445588,0.0003307668,0.0001344831,0.0001037266,0.000001478455],"category_scores_gemma":[0.000008320865,0.0001608365,0.00007711227,0.000226866,0.00002317711,0.000211109,0.000007002358,0.0004922856,5.502056e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001776892,"about_ca_system_score_gemma":0.00001781851,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003442336,"about_ca_topic_score_gemma":0.000009462753,"domain_scores_codex":[0.9986809,0.0001610298,0.0002725442,0.0004790966,0.0001062443,0.0003001574],"domain_scores_gemma":[0.9992652,0.0002883426,0.00005577549,0.000195601,0.00007804204,0.0001170559],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000006395853,0.00001819663,0.00004052971,0.00004164933,0.00001735213,0.000004672857,0.0004796546,0.9436193,0.00006974196,0.0005662751,0.000006344307,0.05512989],"study_design_scores_gemma":[0.0003813838,0.00008019608,0.000009729147,0.0001000984,0.00001573537,0.00006672371,0.0002566566,0.9984899,0.00002241093,0.00005621519,0.0003492982,0.000171681],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0901676,0.001527554,0.9065905,0.0001454422,0.001213618,0.0001537698,4.312675e-7,0.0001472285,0.00005390404],"genre_scores_gemma":[0.9942338,0.00009527642,0.004839833,0.00006258862,0.0001446459,0.00004037041,8.553282e-7,0.00001695991,0.0005656048],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9040663,"threshold_uncertainty_score":0.6558722,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02569691609597778,"score_gpt":0.2534840215965892,"score_spread":0.2277871055006114,"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."}}