{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006031372,0.0003321935,0.0003519269,0.0003289302,0.0003317716,0.0002366424,0.001076233,0.0004008202,0.00004032769],"category_scores_gemma":[0.0001376262,0.0004116727,0.0002909404,0.0003672776,0.00009400814,0.0004526465,0.0006755996,0.0008197965,0.0003778595],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002827878,"about_ca_system_score_gemma":0.0003284419,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002797398,"about_ca_topic_score_gemma":0.00001258608,"domain_scores_codex":[0.9976079,0.0002853241,0.0002776811,0.001253629,0.0001456949,0.0004297348],"domain_scores_gemma":[0.9981218,0.000272832,0.0004793237,0.0007385761,0.0002165745,0.000170916],"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":[0.000149406,0.0001509176,0.003142379,0.0001215172,0.0001428397,0.00005396236,0.001516904,0.5163244,0.000387849,0.4723505,0.0007515278,0.004907783],"study_design_scores_gemma":[0.001858558,0.0000816357,0.003717642,0.00004676042,0.00003503147,0.000002621412,0.000617926,0.9569543,0.00002750845,0.002580746,0.0335958,0.0004814443],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02373567,0.00001994202,0.9671354,0.00009933329,0.001175245,0.0006694497,0.00000977977,0.0003549322,0.006800282],"genre_scores_gemma":[0.9669265,0.00003455742,0.02481685,0.0001026776,0.0001642001,0.000004255929,0.0001169522,0.00003205446,0.007801949],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9431908,"threshold_uncertainty_score":0.9998335,"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."}}