{"id":"W4285044505","doi":"10.22215/etd/2022-15023","title":"Multi-Domain Text Classification with Adversarial Training","year":2022,"lang":"en","type":"dissertation","venue":"","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Carleton University","funders":"","keywords":"Discriminative model; Adversarial system; Computer science; Artificial intelligence; Machine learning; Domain (mathematical analysis); Divergence (linguistics); Invariant (physics); Natural language processing; Pattern recognition (psychology); Mathematics","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":[0.001969619,0.001354169,0.001301053,0.0007006016,0.0005598131,0.0008267124,0.001767632,0.00185516,0.002867666],"category_scores_gemma":[0.005280795,0.0004881283,0.000982643,0.0008462314,0.001313808,0.001705157,0.002254546,0.002880448,0.001394987],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008775285,"about_ca_system_score_gemma":0.000715823,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002065878,"about_ca_topic_score_gemma":0.002300289,"domain_scores_codex":[0.999194,0.0002546404,0.00003568309,0.0002818996,0.0001334501,0.0001003399],"domain_scores_gemma":[0.9970021,0.002017349,0.0001878396,0.0004059163,0.000265275,0.0001216291],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002477917,0.0001492231,0.0008150224,0.0001260471,0.00009105226,0.0001311663,0.00008282025,0.8472207,0.003172404,0.01705118,0.009673029,0.1212396],"study_design_scores_gemma":[0.000005523315,0.00001684841,0.00005284792,0.000005018271,0.000004211899,0.00001564752,0.000004892127,0.9931693,0.000518455,0.005825853,0.0003774127,0.00000400388],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02154355,0.001035944,0.9713894,0.0009067253,0.0002706249,0.000100996,0.0002083769,0.001177509,0.003366892],"genre_scores_gemma":[0.7083398,0.0009118228,0.2672017,0.001276235,0.0005919368,0.0003680986,0.001645338,0.0002742691,0.01939083],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002867666,"threshold_uncertainty_score":0.01041645,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04802985171484224,"score_gpt":0.2889567366978705,"score_spread":0.2409268849830283,"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."}}