{"id":"W4386429868","doi":"10.1007/978-981-99-5837-5_25","title":"Novel Topic Models for Parallel Topics Extraction from Multilingual Text","year":2023,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Topic Modeling","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"ca_institutions":"Concordia University","funders":"","keywords":"Computer science; Jaccard index; Topic model; Flexibility (engineering); Inference; Latent Dirichlet allocation; Prior probability; Artificial intelligence; Dirichlet distribution; Information retrieval; Natural language processing; Machine learning; Data mining; Pattern recognition (psychology); Mathematics; Boundary value problem; Statistics","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005499564,0.0004576583,0.0004788805,0.0004605127,0.0002358267,0.0004433673,0.002571154,0.0004688227,0.000006016096],"category_scores_gemma":[0.0001219401,0.0004511383,0.000175836,0.0002660289,0.000179653,0.0007056035,0.0008953154,0.0007066015,0.00002276236],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002101243,"about_ca_system_score_gemma":0.0004002473,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001463493,"about_ca_topic_score_gemma":0.0002158015,"domain_scores_codex":[0.9962635,0.00001438458,0.0005809853,0.001763824,0.0007548259,0.0006224975],"domain_scores_gemma":[0.9972254,0.0007660614,0.0002520033,0.001386512,0.0002320695,0.000137966],"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":[0.00000417501,0.00001732322,0.000003557674,0.00001977193,0.000009625659,0.00001396265,0.0006412416,0.371158,0.0001549366,0.04243465,0.000008190159,0.5855345],"study_design_scores_gemma":[0.0002791068,0.00003991693,0.00002208178,0.0001245239,0.000005918645,0.000008446872,2.323167e-7,0.7183104,0.000291659,0.2797533,0.0008142239,0.0003501896],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0000914612,0.0001735596,0.992734,0.001225385,0.004183527,0.0005667876,0.0000181024,0.0003038075,0.0007033978],"genre_scores_gemma":[0.01563171,0.00003351158,0.9792724,0.0008037314,0.001642928,0.00003111054,0.00001492836,0.00004605041,0.002523582],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.5851843,"threshold_uncertainty_score":0.9997941,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06478765766729977,"score_gpt":0.2963527200690191,"score_spread":0.2315650624017193,"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."}}