{"id":"W2964416840","doi":"10.24963/ijcai.2019/246","title":"Augmenting Transfer Learning with Semantic Reasoning","year":2019,"lang":"en","type":"preprint","venue":"","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"Thales (Canada)","funders":"National Natural Science Foundation of China","keywords":"Computer science; Transfer of learning; Exploit; Semantics (computer science); Artificial intelligence; Semantic Web; Quality (philosophy); Transfer (computing); Semantic computing; Knowledge transfer; Machine learning; Natural language processing; Knowledge management; Programming language","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":[0.0006625421,0.0003411545,0.0003781905,0.0002031902,0.0002210172,0.0007920834,0.0009406537,0.0001833386,0.000139676],"category_scores_gemma":[0.00004673982,0.0002903526,0.0001283961,0.0002624415,0.00003273992,0.000337246,0.000633003,0.001341961,0.0002614646],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005975554,"about_ca_system_score_gemma":0.0002088591,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006766991,"about_ca_topic_score_gemma":0.0000120752,"domain_scores_codex":[0.9975622,0.0001816462,0.0003310581,0.0008985902,0.0005500231,0.0004765318],"domain_scores_gemma":[0.9988323,0.000127014,0.0001319989,0.0006784748,0.0001139136,0.0001162679],"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":[0.00002985905,0.00007588536,0.01331688,0.0005019387,0.0002732382,0.0001018163,0.009505261,0.8221554,0.0004910564,0.0967887,0.0002025066,0.05655748],"study_design_scores_gemma":[0.0006470831,0.0001043496,0.002600728,0.0007287505,0.0000351645,0.0000351093,0.0005037815,0.9856437,0.0002942093,0.000315503,0.008324984,0.0007665693],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02639681,0.0001074326,0.9095003,0.0003208278,0.0004141922,0.0002923711,2.502771e-7,0.0006864187,0.06228138],"genre_scores_gemma":[0.8880591,0.00002231213,0.09965716,0.0002594255,0.00006942132,0.00001947795,0.00001260203,0.00003983673,0.01186069],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8616623,"threshold_uncertainty_score":0.9999549,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01620833704284038,"score_gpt":0.2351116021474014,"score_spread":0.218903265104561,"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."}}