{"id":"W3175570208","doi":"10.1609/aaai.v35i12.17323","title":"Multi-task Learning by Leveraging the Semantic Information","year":2021,"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":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"Vector Institute; Université Laval","funders":"Natural Sciences and Engineering Research Council of Canada; China Scholarship Council","keywords":"Computer science; Leverage (statistics); Artificial intelligence; Machine learning; Task (project management); Divergence (linguistics); Multi-task learning; Matching (statistics); Semantic space; Kullback–Leibler divergence; Semantic matching; Generalization; Mathematics; Statistics","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":[0.0006751583,0.0001705441,0.0001677951,0.00007233454,0.0004975229,0.0007092057,0.00130406,0.00006093099,0.00008028224],"category_scores_gemma":[0.0009369909,0.0001179771,0.00009799848,0.0007306117,0.0001492322,0.0009378882,0.000371968,0.0005034826,0.0001768117],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003650834,"about_ca_system_score_gemma":0.0001101647,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003164995,"about_ca_topic_score_gemma":0.00000436104,"domain_scores_codex":[0.9983655,0.00004884087,0.0004827312,0.0002960729,0.0005101024,0.0002967915],"domain_scores_gemma":[0.9984548,0.0001351123,0.0004008763,0.0002381491,0.0007075618,0.00006349706],"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":[0.00002549182,0.0001356646,0.0006362316,0.00006514104,0.00003520608,0.000001079375,0.01751071,0.001989763,0.1232818,0.5835493,0.0008031395,0.2719664],"study_design_scores_gemma":[0.0000652416,0.00006711928,0.0004848241,0.0001898011,0.00001292427,0.00001443658,0.006532048,0.693305,0.2792606,0.01259775,0.007186706,0.0002835999],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0762993,0.000112603,0.8901395,0.01633298,0.0008555255,0.0004895889,0.000003535681,0.0002543001,0.01551265],"genre_scores_gemma":[0.9942475,0.00004547309,0.004141366,0.0007839262,0.00002571672,0.00001376744,0.00000193239,0.00000741046,0.0007329113],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9179482,"threshold_uncertainty_score":0.6838887,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0598701591180961,"score_gpt":0.2760216873527879,"score_spread":0.2161515282346918,"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."}}