{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003467151,0.0001692347,0.0002565535,0.00009406928,0.0005632996,0.0003092631,0.001564478,0.00009033712,0.00001256892],"category_scores_gemma":[0.0004302004,0.0001527447,0.00008098491,0.0001109889,0.0002595642,0.0002943865,0.0003536538,0.0004028697,0.0000212277],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003987464,"about_ca_system_score_gemma":0.0001422439,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00195044,"about_ca_topic_score_gemma":0.0002271424,"domain_scores_codex":[0.9986991,0.0001242628,0.0002103369,0.0004236725,0.0002263377,0.0003162904],"domain_scores_gemma":[0.99741,0.000133922,0.0004132948,0.001741741,0.0001842898,0.0001167324],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002584789,0.0005040837,0.2480697,0.0002071754,0.00008272056,0.00004400148,0.001085338,0.003207328,0.6384877,0.03800906,0.0004675192,0.06957694],"study_design_scores_gemma":[0.0006977375,0.0003153392,0.1126539,0.000009252974,0.00000818648,0.00001071671,0.000007973726,0.7799831,0.1048147,0.0001078983,0.001179958,0.0002113021],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8764413,0.000009941485,0.1072592,0.01421796,0.0001213708,0.0002458559,0.000004070001,0.0001878275,0.001512467],"genre_scores_gemma":[0.9080482,0.000002811162,0.08976924,0.0001373863,0.00004221755,0.00001452846,0.000004365429,0.00001293587,0.001968293],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7767758,"threshold_uncertainty_score":0.6228746,"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."}}