{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002284786,0.001836868,0.001262004,0.001180821,0.0007359925,0.001177507,0.002399792,0.001694422,0.003721357],"category_scores_gemma":[0.007878719,0.0005417108,0.001162933,0.001133261,0.001285516,0.003638626,0.004110384,0.002411386,0.001508953],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007244998,"about_ca_system_score_gemma":0.0009960533,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001540286,"about_ca_topic_score_gemma":0.003004206,"domain_scores_codex":[0.998987,0.0002963162,0.00006415405,0.0002532879,0.000305636,0.00009361104],"domain_scores_gemma":[0.9978376,0.000865467,0.0002108214,0.0005179485,0.0004065083,0.0001617537],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.001019453,0.0009732406,0.004313557,0.0007230586,0.0002828823,0.0005879305,0.0007292983,0.1241878,0.07783119,0.01776155,0.02621935,0.7453707],"study_design_scores_gemma":[0.00008264804,0.0002700526,0.000811004,0.00002936434,0.00004591689,0.000147577,0.00007815316,0.9479072,0.03167957,0.01357165,0.005334093,0.00004274455],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02609389,0.0003212005,0.9662712,0.0004009099,0.0001028669,0.0002144253,0.0003482464,0.00522093,0.001026271],"genre_scores_gemma":[0.4218812,0.0004446854,0.5634837,0.001048978,0.0003118816,0.0008637222,0.002614571,0.001037784,0.008313634],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003721357,"threshold_uncertainty_score":0.0124492,"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."}}