{"id":"W2973285246","doi":"10.48550/arxiv.1909.08203","title":"Dual Adversarial Co-Learning for Multi-Domain Text Classification","year":2019,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Carleton University","funders":"","keywords":"Adversarial system; Computer science; Dual (grammatical number); Generalization; Artificial intelligence; Domain (mathematical analysis); Machine learning; Feature (linguistics); Feature extraction; Pattern recognition (psychology); Labeled data; 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":[0.002927676,0.001380885,0.001567282,0.001062447,0.0006229752,0.001124036,0.002422403,0.002186765,0.002164031],"category_scores_gemma":[0.006165622,0.0004964927,0.0009474431,0.001156518,0.001636251,0.002808271,0.002780556,0.003565649,0.00122503],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009961548,"about_ca_system_score_gemma":0.0007952251,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001312398,"about_ca_topic_score_gemma":0.001016841,"domain_scores_codex":[0.9980286,0.0007675713,0.0000712307,0.0005672758,0.0003855116,0.0001798086],"domain_scores_gemma":[0.9956995,0.002570191,0.000390539,0.0006802735,0.0004492463,0.0002102515],"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":[0.0004676502,0.000364256,0.002050648,0.0001694012,0.0001727957,0.0002166268,0.0001394511,0.762121,0.006996203,0.02836861,0.006592674,0.1923407],"study_design_scores_gemma":[0.000004446988,0.00002001823,0.00005995721,0.000002819274,0.000003731848,0.00001700876,0.00000444252,0.9929209,0.0007939942,0.005875248,0.0002930178,0.000004392229],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01066298,0.0003423151,0.9872327,0.0003021084,0.00005524468,0.00003584266,0.00006216986,0.0004728035,0.0008338994],"genre_scores_gemma":[0.7505979,0.0003923435,0.2391787,0.0006426001,0.0003087271,0.0002654406,0.0009396212,0.0002034994,0.007471198],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.002927676,"threshold_uncertainty_score":0.0154832,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1491319453894409,"score_gpt":0.2404427124296455,"score_spread":0.09131076704020458,"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."}}