{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002424701,0.001699713,0.001097672,0.001094296,0.0006611468,0.00116132,0.002273037,0.001958193,0.004149738],"category_scores_gemma":[0.009747388,0.0005732201,0.001094366,0.000833326,0.0008050945,0.003022537,0.001923326,0.002633922,0.004216004],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008247124,"about_ca_system_score_gemma":0.00145562,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003033147,"about_ca_topic_score_gemma":0.005786602,"domain_scores_codex":[0.9985883,0.0003961363,0.00009729808,0.0004351655,0.000347446,0.0001356241],"domain_scores_gemma":[0.9975714,0.001067624,0.0002474141,0.0006111818,0.0003799964,0.0001223243],"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":[0.001212051,0.0005213541,0.004077036,0.0004613518,0.000223248,0.000486146,0.0006749739,0.134455,0.09920325,0.01582203,0.04938934,0.6934744],"study_design_scores_gemma":[0.00004243423,0.00008153687,0.0005100917,0.00002262121,0.00001895636,0.0001151671,0.000044428,0.9662064,0.01834574,0.01035605,0.004224127,0.00003249068],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03373346,0.0006561287,0.9444998,0.0006601454,0.0002405967,0.0001528648,0.0007749643,0.01750641,0.00177563],"genre_scores_gemma":[0.3464859,0.0003622357,0.6383067,0.0008092491,0.0003076383,0.0005019471,0.003095326,0.0021539,0.007977019],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004149738,"threshold_uncertainty_score":0.01388222,"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."}}