{"id":"W3110664450","doi":"10.1609/aaai.v35i15.17601","title":"MASKER: Masked Keyword Regularization for Reliable Text Classification","year":2021,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Topic Modeling","field":"Computer Science","cited_by":28,"is_retracted":false,"has_abstract":true,"ca_institutions":"Kootenay Association for Science & Technology","funders":"Defense Acquisition Program Administration; Agency for Defense Development","keywords":"Computer science; Regularization (linguistics); Artificial intelligence; Inference; Natural language processing; Context (archaeology); Generalization; Domain (mathematical analysis); Code (set theory); Pattern recognition (psychology); Speech recognition; Machine learning; Mathematics; Set (abstract data type)","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":[0.0004688904,0.0001712106,0.0002107559,0.00008559362,0.000224068,0.0003056851,0.001312742,0.0001137682,0.00003585733],"category_scores_gemma":[0.0006021843,0.0001459957,0.0001161693,0.0006705938,0.00009554016,0.0004460016,0.000263325,0.0001778045,0.00003592954],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006111784,"about_ca_system_score_gemma":0.0001886429,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008313697,"about_ca_topic_score_gemma":0.00000393226,"domain_scores_codex":[0.998126,0.00001433233,0.0005498489,0.0006083623,0.0004033109,0.0002981094],"domain_scores_gemma":[0.9977065,0.00008027904,0.0003598252,0.0004748735,0.001313316,0.00006518644],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00001658551,0.00006703925,0.00006891284,0.00004039987,0.000007096819,1.670688e-7,0.0004862007,0.0001222185,0.09778082,0.8598765,0.000161579,0.0413725],"study_design_scores_gemma":[0.00002340626,0.00004078071,0.00008700052,0.0001020662,0.000008009385,0.000002501909,0.0003522494,0.3036117,0.4261465,0.2690599,0.0004453054,0.0001205961],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02873969,0.000028325,0.943043,0.0131107,0.0007565086,0.000606298,0.000004253255,0.0001394885,0.01357177],"genre_scores_gemma":[0.951324,0.00003327917,0.0455121,0.0002571035,0.00009010803,0.00006214088,0.000002280409,0.00001371442,0.002705246],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9225844,"threshold_uncertainty_score":0.5953534,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.108584551329108,"score_gpt":0.2992483494078932,"score_spread":0.1906637980787853,"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."}}