{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004920984,0.002353086,0.002424133,0.001996951,0.001154425,0.002031474,0.003465683,0.002912126,0.00185947],"category_scores_gemma":[0.01304209,0.0007503347,0.001784467,0.001958958,0.001575373,0.005736191,0.004844936,0.004358952,0.001019264],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001256883,"about_ca_system_score_gemma":0.00233291,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002905435,"about_ca_topic_score_gemma":0.003264702,"domain_scores_codex":[0.9963759,0.001156845,0.0001951196,0.001284675,0.0006775804,0.0003098763],"domain_scores_gemma":[0.9945497,0.003082483,0.0004264842,0.0008951022,0.0006897323,0.0003564905],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0006880096,0.001051923,0.004270258,0.0005050526,0.0003626796,0.0002926316,0.0005635594,0.3670233,0.01680596,0.01668319,0.008306423,0.583447],"study_design_scores_gemma":[0.00003343735,0.00009256541,0.0004547068,0.00001570319,0.00002987078,0.00006555913,0.00005729522,0.9636413,0.002746224,0.03172916,0.001108983,0.00002510248],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02060727,0.0005373235,0.9758522,0.0004514902,0.00008332994,0.0001292743,0.0001335937,0.001050671,0.001154901],"genre_scores_gemma":[0.5927609,0.0004111339,0.4003305,0.0009115582,0.0003142525,0.0004558922,0.001254723,0.0003714195,0.003189731],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004920984,"threshold_uncertainty_score":0.026025,"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."}}