{"id":"W4377018759","doi":"10.32473/flairs.36.133326","title":"Improving Word Embedding Using Variational Dropout","year":2023,"lang":"en","type":"article","venue":"Proceedings of the ... International Florida Artificial Intelligence Research Society Conference","topic":"Topic Modeling","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa; Carleton University","funders":"","keywords":"Dropout (neural networks); Word (group theory); Computer science; Word embedding; Artificial intelligence; Overfitting; Orthogonality; Natural language processing; Embedding; Curse of dimensionality; Inference; Machine learning; Mathematics; Artificial neural network","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":[0.003455847,0.0001938136,0.0002053183,0.0002582893,0.0006139872,0.0008061012,0.004125287,0.0001270171,0.0000657112],"category_scores_gemma":[0.001488146,0.0001678292,0.000258524,0.001849985,0.0003065518,0.001138562,0.0024391,0.0006988443,0.0000664264],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003636732,"about_ca_system_score_gemma":0.0005077656,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002745563,"about_ca_topic_score_gemma":0.000006455823,"domain_scores_codex":[0.9956858,0.00003266134,0.0006569643,0.0006868811,0.00226242,0.0006753307],"domain_scores_gemma":[0.9960703,0.0004141316,0.0002797954,0.0003151488,0.002799976,0.0001206595],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001375613,0.00004150502,0.0007072125,0.00005660216,0.00006638886,0.00000100113,0.003320102,0.005313184,0.1588532,0.8031308,0.0005694106,0.02792683],"study_design_scores_gemma":[0.00002465488,0.0000143209,0.00007469109,0.0001047648,0.00000387208,0.000004232504,0.001965705,0.8147879,0.05835484,0.1243828,0.0001444237,0.0001378164],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2484116,0.000022422,0.7389196,0.007011036,0.002358871,0.0004880824,0.00001252377,0.0002630567,0.002512876],"genre_scores_gemma":[0.9528213,0.00004321376,0.04595847,0.00006658696,0.0005772361,0.00003551517,0.000002047158,0.00001744114,0.0004782521],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8094747,"threshold_uncertainty_score":0.7773253,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1990856946383329,"score_gpt":0.3984730303623926,"score_spread":0.1993873357240597,"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."}}