{"id":"W2963172229","doi":"10.1609/aaai.v33i01.33016762","title":"Contextualized Non-Local Neural Networks for Sequence Learning","year":2019,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Topic Modeling","field":"Computer Science","cited_by":53,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"Science and Technology Commission of Shanghai Municipality; Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China","keywords":"Interpretability; Computer science; Artificial intelligence; Leverage (statistics); Artificial neural network; Sentence; Machine learning; Sequence learning; Transformer; Natural language processing","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":[0.0008966445,0.0008310839,0.0007821267,0.0008723526,0.0003171663,0.0005902689,0.001481981,0.001009936,0.0032473],"category_scores_gemma":[0.003306682,0.0004084782,0.0006150447,0.00125788,0.0006447702,0.001874794,0.0009053024,0.001638762,0.0008298818],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001057505,"about_ca_system_score_gemma":0.0007011627,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006113355,"about_ca_topic_score_gemma":0.01037784,"domain_scores_codex":[0.9995381,0.0001654094,0.00002390883,0.0001663284,0.00007178696,0.00003456518],"domain_scores_gemma":[0.9990741,0.0005275928,0.00008632776,0.0001485564,0.0001272052,0.00003622142],"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":[0.0001491714,0.00008649911,0.0008313332,0.0002237364,0.0001067137,0.0001366147,0.0001296267,0.7261063,0.005802841,0.05202677,0.00360927,0.2107911],"study_design_scores_gemma":[0.000003642053,0.0000177869,0.00008710247,0.000006309815,0.000006632574,0.00001014038,0.000004719815,0.9747354,0.0005168628,0.02387944,0.0007271992,0.000004782538],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.007718838,0.001052711,0.9887905,0.0002368711,0.0000431716,0.00003001054,0.0001584326,0.0009475252,0.001021911],"genre_scores_gemma":[0.5728072,0.00203261,0.4168266,0.0004481056,0.0002613201,0.0003584503,0.001310613,0.0002795101,0.00567572],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006113355,"threshold_uncertainty_score":0.01215553,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09166343411648817,"score_gpt":0.3109315896493073,"score_spread":0.2192681555328192,"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."}}