{"id":"W2905514808","doi":"10.1609/aaai.v33i01.33014360","title":"Learning Multi-Task Communication with Message Passing for Sequence Learning","year":2019,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Advanced Graph Neural Networks","field":"Computer Science","cited_by":20,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University; Polytechnique Montréal","funders":"Science and Technology Commission of Shanghai Municipality; Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China","keywords":"Computer science; Task (project management); Sequence learning; Artificial intelligence; Graph; Multi-task learning; Machine learning; Sequence (biology); Transfer of learning; Message passing; Natural language processing; Theoretical computer science; Distributed computing","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":[0.003596226,0.001867001,0.001488874,0.001099052,0.0008395895,0.001490574,0.004100163,0.00308665,0.004520966],"category_scores_gemma":[0.01144787,0.0006377219,0.001318423,0.001163574,0.001564657,0.005269406,0.003042262,0.004377267,0.001464285],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001911273,"about_ca_system_score_gemma":0.002076776,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005039288,"about_ca_topic_score_gemma":0.005446265,"domain_scores_codex":[0.998125,0.0008205807,0.00008715021,0.0004772291,0.0002788338,0.0002112661],"domain_scores_gemma":[0.9950799,0.002528962,0.0003699169,0.001085419,0.0005939397,0.0003418759],"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":[0.0006848202,0.0006844829,0.001324829,0.0003309631,0.0001920556,0.0001999931,0.0003765274,0.6281496,0.006434213,0.04760401,0.007455935,0.3065625],"study_design_scores_gemma":[0.00001772605,0.0000608134,0.00006426331,0.000006006293,0.00001130629,0.00001224067,0.000009969327,0.9710193,0.001441827,0.02671557,0.0006306803,0.00001029389],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.009790012,0.0002157845,0.9869667,0.0004581251,0.00009672752,0.00009036829,0.00008273055,0.001429229,0.0008703518],"genre_scores_gemma":[0.574773,0.000332922,0.4149522,0.0006070308,0.0002486541,0.0007692114,0.0007237966,0.0003072818,0.007285957],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005039288,"threshold_uncertainty_score":0.01901889,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07632874879394373,"score_gpt":0.3076339576096807,"score_spread":0.2313052088157369,"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."}}