{"id":"W2617136920","doi":"10.24963/ijcai.2017/178","title":"How a General-Purpose Commonsense Ontology can Improve Performance of Learning-Based Image Retrieval","year":2017,"lang":"en","type":"article","venue":"","topic":"Multimodal Machine Learning Applications","field":"Computer Science","cited_by":17,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"Comisión Nacional de Investigación Científica y Tecnológica","keywords":"Commonsense knowledge; Computer science; Ontology; Exploit; Commonsense reasoning; Artificial intelligence; Information retrieval; Natural language processing; Question answering; Testbed; Sentence; Visualization; Knowledge retrieval; Benchmark (surveying); Knowledge representation and reasoning; Knowledge extraction; World Wide Web","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":[0.003039151,0.001374503,0.001117203,0.002465591,0.001080786,0.001876689,0.001880882,0.001796992,0.003873275],"category_scores_gemma":[0.008625686,0.0003156592,0.001117977,0.002184775,0.0008267353,0.007678316,0.002098649,0.001646766,0.002048275],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001621761,"about_ca_system_score_gemma":0.001750607,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01677926,"about_ca_topic_score_gemma":0.0205619,"domain_scores_codex":[0.9983332,0.0003356299,0.0001834923,0.0004321822,0.0005154965,0.0002000141],"domain_scores_gemma":[0.9978396,0.0007454689,0.0001067612,0.000809336,0.0004101795,0.0000885765],"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":[0.0005801807,0.0006623131,0.005440736,0.0006957403,0.0002456834,0.0002102266,0.0002820277,0.042104,0.03510701,0.009381592,0.02876346,0.8765271],"study_design_scores_gemma":[0.0001568907,0.000578171,0.004442497,0.0001214024,0.0003296199,0.000625949,0.0007068621,0.8471454,0.06802908,0.03834158,0.03940842,0.0001140924],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3870888,0.007241603,0.5387638,0.002898473,0.0007332389,0.0007828316,0.003591093,0.03163156,0.02726861],"genre_scores_gemma":[0.693978,0.001244741,0.2911924,0.0007474875,0.00009908764,0.000121801,0.008331842,0.0004517073,0.003832861],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01677926,"threshold_uncertainty_score":0.03336316,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01406294622160557,"score_gpt":0.269845979589982,"score_spread":0.2557830333683764,"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."}}