{"id":"W4385573553","doi":"10.18653/v1/2022.emnlp-main.57","title":"DropMix: A Textual Data Augmentation Combining Dropout with Mixup","year":2022,"lang":"en","type":"article","venue":"","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa","funders":"Fundamental Research Funds for the Central Universities; State Key Laboratory of Software Development Environment; Leverhulme Trust","keywords":"Overfitting; Dropout (neural networks); Computer science; Regularization (linguistics); Artificial intelligence; Machine learning; Curse of dimensionality; Deep neural networks; Deep learning; 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":[0.0004417185,0.00007465352,0.0000699503,0.00007249088,0.0003859556,0.0001544689,0.001417219,0.000009845334,0.0002384029],"category_scores_gemma":[0.00002302042,0.00006333202,0.00000881714,0.0003318681,0.00002096283,0.0005610884,0.001096613,0.0001723735,0.00005654146],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003564651,"about_ca_system_score_gemma":0.00007641657,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002261084,"about_ca_topic_score_gemma":0.0000247002,"domain_scores_codex":[0.9987939,0.0001318812,0.0001277499,0.0004319483,0.0003757883,0.0001387233],"domain_scores_gemma":[0.9986745,0.00006473225,0.00008419645,0.001111585,0.00001978987,0.00004517207],"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":[0.00007171506,0.0004778822,0.02466184,0.00002132873,0.00006692846,0.00004159159,0.003290769,0.002332287,0.001646251,0.6156195,0.06652153,0.2852483],"study_design_scores_gemma":[0.0007134964,0.0002688674,0.004124101,0.000004068726,0.00000815898,0.00005927001,0.001292,0.9154134,0.00006201353,0.0003183262,0.07753307,0.0002032118],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.009663345,0.00002217809,0.9692967,0.003523385,0.000136545,0.0001325046,0.00002864683,0.000350371,0.01684631],"genre_scores_gemma":[0.9554904,0.000001495703,0.04115862,0.0005416705,0.00002103751,0.00002206736,0.000904386,0.000006799017,0.001853508],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9458271,"threshold_uncertainty_score":0.2968498,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03726976908270862,"score_gpt":0.2831414758018327,"score_spread":0.2458717067191241,"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."}}