{"id":"W2570431255","doi":"10.1162/tacl_a_00077","title":"Aspect-augmented Adversarial Networks for Domain Adaptation","year":2017,"lang":"en","type":"article","venue":"Transactions of the Association for Computational Linguistics","topic":"Topic Modeling","field":"Computer Science","cited_by":93,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"Army Research Office","keywords":"Computer science; Adversarial system; Domain adaptation; Classifier (UML); Artificial intelligence; Transfer of learning; Sentence; Training set; Domain (mathematical analysis); Relevance (law); Natural language processing; Machine learning; Invariant (physics)","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":[0.001155514,0.001174908,0.0007708182,0.0005491431,0.0002576981,0.0007745214,0.001383874,0.000879649,0.002353759],"category_scores_gemma":[0.003794324,0.0003735103,0.0007593727,0.0007037246,0.0007265564,0.001420522,0.001951448,0.002241588,0.001126001],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005888284,"about_ca_system_score_gemma":0.000507691,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001275426,"about_ca_topic_score_gemma":0.001758937,"domain_scores_codex":[0.9994262,0.000221692,0.00002692244,0.0001440107,0.0001298454,0.00005128136],"domain_scores_gemma":[0.9990277,0.0004648296,0.00009732901,0.0002330008,0.0001323918,0.00004471513],"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":[0.000171961,0.0001144857,0.001572256,0.0001372483,0.0001350797,0.0001764332,0.0001745366,0.7355163,0.008301347,0.03332645,0.009190292,0.2111837],"study_design_scores_gemma":[0.000005125274,0.00001887774,0.000114613,0.000006876458,0.000007505732,0.00003130525,0.000006539952,0.9847269,0.0009373505,0.01257219,0.001566447,0.000006243788],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.009802936,0.0004252828,0.9858505,0.0002148425,0.00007480339,0.0000467896,0.0001502762,0.0009782031,0.002456237],"genre_scores_gemma":[0.6915725,0.001018249,0.2935808,0.0007031672,0.0002706828,0.000406338,0.001500462,0.0003959498,0.0105519],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002353759,"threshold_uncertainty_score":0.007874131,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02543341488488058,"score_gpt":0.2719049047599099,"score_spread":0.2464714898750293,"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."}}