{"id":"W3101703188","doi":"10.18653/v1/2020.findings-emnlp.44","title":"ConceptBert: Concept-Aware Representation for Visual Question Answering","year":2020,"lang":"en","type":"article","venue":"","topic":"Multimodal Machine Learning Applications","field":"Computer Science","cited_by":142,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University; Thales (Canada)","funders":"","keywords":"Question answering; Computer science; Embedding; Commonsense knowledge; Artificial intelligence; Exploit; Natural language processing; Natural language; Knowledge representation and reasoning; Focus (optics); Representation (politics); Information retrieval","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00007824943,0.00008625643,0.0000992411,0.00002377348,0.0001202577,0.00009780205,0.0003372112,0.00003870448,0.0000332153],"category_scores_gemma":[0.0001485629,0.00008617806,0.0000456831,0.0002413702,0.00002703375,0.0003268663,0.00009374151,0.00008600225,0.00006150166],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001997848,"about_ca_system_score_gemma":0.00002720636,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001899888,"about_ca_topic_score_gemma":0.000003736307,"domain_scores_codex":[0.999135,0.00004676664,0.0001674452,0.000378728,0.0001288124,0.0001433185],"domain_scores_gemma":[0.9993877,0.000150987,0.00006978777,0.0001990592,0.0000903627,0.0001021335],"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":[0.00003871203,0.0001163332,0.01365061,0.00005996279,0.00004583801,0.000003440662,0.009004581,0.03789169,0.02734868,0.5804636,0.006242948,0.3251336],"study_design_scores_gemma":[0.0003428822,0.00009086822,0.006132839,0.000004489925,0.000003400581,0.00000144379,0.00006659039,0.9833768,0.006880946,0.0005651856,0.002413057,0.0001214727],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01214875,0.00001204638,0.97425,0.01195062,0.00007455575,0.000366606,0.000002348929,0.0005355134,0.0006595608],"genre_scores_gemma":[0.9031045,8.9715e-7,0.09531502,0.001237277,0.0001261193,0.00009134454,0.00002312587,0.000008528144,0.00009316869],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9454851,"threshold_uncertainty_score":0.3514239,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03075027110620818,"score_gpt":0.3548092531981962,"score_spread":0.324058982091988,"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."}}