{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006534018,0.0002493365,0.0003613667,0.0000890796,0.0001982083,0.000261608,0.0022608,0.0001237494,0.00004077971],"category_scores_gemma":[0.000290805,0.0001949135,0.0001774579,0.0004067151,0.0001917344,0.0004845398,0.0004170852,0.0004456662,0.00004800053],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005497221,"about_ca_system_score_gemma":0.00007703328,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004217475,"about_ca_topic_score_gemma":0.000004664814,"domain_scores_codex":[0.9978374,0.00002073931,0.0005870392,0.0006516112,0.0004093158,0.0004938588],"domain_scores_gemma":[0.9982786,0.0002117025,0.0004054852,0.0003551951,0.0006543714,0.00009471399],"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":[0.00009372917,0.00004731311,0.0003750478,0.00005097476,0.00001426942,2.881597e-7,0.0009600315,0.02388887,0.0186838,0.7849715,0.0000382262,0.170876],"study_design_scores_gemma":[0.00006319035,0.0002318162,0.00002727363,0.0001341604,0.00000701207,0.000003856957,0.0004563371,0.9180813,0.05290932,0.02777752,0.00009506576,0.0002131257],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1478033,0.00001902778,0.8457384,0.001572343,0.0008190675,0.0008310212,0.00000153908,0.0001181518,0.003097164],"genre_scores_gemma":[0.9937457,0.00001003342,0.00524472,0.0003273736,0.00008609876,0.00004924053,5.781226e-7,0.00001666869,0.0005195606],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8941925,"threshold_uncertainty_score":0.7948341,"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."}}