{"id":"W4226436280","doi":"10.1109/mlbdbi54094.2021.00140","title":"The Application of Graph Neural Network in Natural Language Processing and Computer Vision","year":2021,"lang":"en","type":"article","venue":"2021 3rd International Conference on Machine Learning, Big Data and Business Intelligence (MLBDBI)","topic":"Advanced Graph Neural Networks","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Categorization; Artificial intelligence; Deep learning; Benchmark (surveying); Graph; Artificial neural network; Euclidean geometry; Recurrent neural network; Transformation (genetics); Machine learning; Natural language processing; Theoretical computer science","routes":{"ca_aff":true,"ca_fund":false,"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":[0.0009164718,0.001194786,0.0007183714,0.002544693,0.0003793855,0.001445781,0.001191275,0.001159553,0.002534557],"category_scores_gemma":[0.00354637,0.0003651844,0.0008919142,0.004131705,0.001148317,0.003325311,0.0009270479,0.001796322,0.0009131156],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001302087,"about_ca_system_score_gemma":0.0008496985,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007751542,"about_ca_topic_score_gemma":0.008573144,"domain_scores_codex":[0.9993091,0.0002039862,0.00004324163,0.0001962801,0.0002105072,0.00003689292],"domain_scores_gemma":[0.9987634,0.0007038703,0.00009213366,0.0001624197,0.0002437855,0.00003430199],"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":[0.0001247132,0.0001234842,0.004612281,0.001759338,0.0002941421,0.0003194869,0.0002228046,0.1600601,0.00646786,0.1267766,0.02434122,0.674898],"study_design_scores_gemma":[0.0000148885,0.0001158943,0.003336386,0.0002812833,0.0000965591,0.0004305952,0.0001198812,0.6652918,0.006595761,0.2660418,0.05759974,0.00007539476],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02549051,0.0399971,0.9044157,0.003353748,0.0007089154,0.0002055646,0.001938521,0.001826332,0.02206363],"genre_scores_gemma":[0.4525007,0.06396711,0.4654541,0.001479433,0.0007717955,0.0003671154,0.005382721,0.0004459263,0.009631076],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007751542,"threshold_uncertainty_score":0.01541287,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03563224655463522,"score_gpt":0.3193743397329246,"score_spread":0.2837420931782894,"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."}}