{"id":"W2997420347","doi":"10.1609/aaai.v34i04.6115","title":"Dual Adversarial Co-Learning for Multi-Domain Text Classification","year":2020,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":26,"is_retracted":false,"has_abstract":true,"ca_institutions":"Carleton University","funders":"Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs","keywords":"Computer science; Classifier (UML); Artificial intelligence; Labeled data; Adversarial system; Machine learning; Domain (mathematical analysis); Generalization; Dual (grammatical number); Pattern recognition (psychology); Mathematics","routes":{"ca_aff":true,"ca_fund":true,"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":[0.002352417,0.001019102,0.001153106,0.0007820398,0.0005015779,0.0008056071,0.001738631,0.001534631,0.001627174],"category_scores_gemma":[0.005063555,0.0003858147,0.0007954486,0.0008945444,0.001345503,0.002150173,0.001931744,0.003131446,0.0007202856],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001048491,"about_ca_system_score_gemma":0.0007255072,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001996454,"about_ca_topic_score_gemma":0.001549358,"domain_scores_codex":[0.9988073,0.0004504467,0.00004946798,0.0003297068,0.0002371616,0.0001259026],"domain_scores_gemma":[0.9967049,0.002010364,0.0003394347,0.0004557351,0.0003302366,0.000159376],"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":[0.0003615049,0.0002754481,0.00187097,0.0001147291,0.00009691498,0.0001930114,0.0001428052,0.8112903,0.006478543,0.02025243,0.005293539,0.1536299],"study_design_scores_gemma":[0.00000313258,0.00001448543,0.00005628171,0.000002132115,0.000002778498,0.00001120414,0.000003887484,0.9953323,0.0006694109,0.003669224,0.0002317784,0.000003280515],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01803944,0.0003994385,0.9795603,0.0003755113,0.00005252796,0.0000358308,0.00005719818,0.0005086495,0.0009711685],"genre_scores_gemma":[0.8102205,0.0004162642,0.1814223,0.000523042,0.0002153275,0.0001959349,0.0006648037,0.0001363869,0.006205451],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002352417,"threshold_uncertainty_score":0.01244092,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2024761734296001,"score_gpt":0.3410998326204007,"score_spread":0.1386236591908006,"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."}}