{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005792981,0.0002099233,0.0002435402,0.00008725714,0.0003570092,0.0003098805,0.0011564,0.0001035677,0.00005167587],"category_scores_gemma":[0.001209626,0.0001765046,0.0001502528,0.0005401844,0.0001922047,0.0004420323,0.0001799444,0.0003886579,0.0001418067],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004162031,"about_ca_system_score_gemma":0.0001186901,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005825926,"about_ca_topic_score_gemma":0.000002053719,"domain_scores_codex":[0.998084,0.00003644052,0.0005395621,0.0005567504,0.0004522392,0.0003310221],"domain_scores_gemma":[0.9985335,0.0001505906,0.0004874418,0.0001446814,0.0005343086,0.0001494707],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001367705,0.00007458447,0.0001365053,0.00003309081,0.00001420552,2.495154e-7,0.004810017,0.0002529714,0.07549817,0.8453203,0.0002254475,0.07349765],"study_design_scores_gemma":[0.0001676849,0.0003994336,0.0004317245,0.0000711972,0.00001179992,0.000002104435,0.003860395,0.8761742,0.09724208,0.01429023,0.007052367,0.0002968636],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01730437,0.00001099097,0.9580839,0.009865763,0.0004312019,0.0007850098,0.000004362897,0.0002294656,0.0132849],"genre_scores_gemma":[0.968988,0.000009587442,0.02996108,0.0005758952,0.000157988,0.0000435847,0.000002211852,0.00001647427,0.0002451937],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9516836,"threshold_uncertainty_score":0.7197651,"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."}}