{"id":"W2798881773","doi":"10.18653/v1/p18-1085","title":"Illustrative Language Understanding: Large-Scale Visual Grounding with Image Search","year":2018,"lang":"en","type":"article","venue":"","topic":"Multimodal Machine Learning Applications","field":"Computer Science","cited_by":51,"is_retracted":false,"has_abstract":true,"ca_institutions":"Google (Canada)","funders":"","keywords":"Computer science; Artificial intelligence; Natural language processing; Sentence; Word (group theory); Embedding; Image (mathematics); Semantics (computer science); Inference; Vocabulary; Speech recognition; Linguistics","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":[0.0003335811,0.0001264861,0.0001072406,0.0001061271,0.0003913017,0.0002653838,0.0004657886,0.00004002467,0.000288704],"category_scores_gemma":[0.00001864387,0.00009720951,0.00002641009,0.0005684016,0.0001668995,0.0004016343,0.0002112163,0.0002126137,0.0004095622],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001114942,"about_ca_system_score_gemma":0.00005899305,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003297785,"about_ca_topic_score_gemma":0.0002563526,"domain_scores_codex":[0.9987199,0.00007485694,0.0001157594,0.0004162722,0.000301909,0.0003712679],"domain_scores_gemma":[0.9992937,0.0001192226,0.00004213957,0.0003452163,0.00008282599,0.000116873],"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":[0.00005500515,0.000456423,0.02208818,0.00003438432,0.00008608816,0.00004062745,0.05414434,0.00005636201,0.01677567,0.8995905,0.0006970308,0.005975399],"study_design_scores_gemma":[0.001659119,0.0009819575,0.03889241,0.00006151213,0.00001628801,0.00006643925,0.02302944,0.921223,0.01109026,0.001960321,0.0003195701,0.0006997074],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2166141,0.00000306667,0.7548577,0.0007527534,0.00002742025,0.0001468867,0.000001340713,0.0002842276,0.02731249],"genre_scores_gemma":[0.8884321,3.176216e-7,0.1105395,0.0001528383,0.0001049597,0.00001250552,0.000004078342,0.00001252673,0.000741149],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9211666,"threshold_uncertainty_score":0.526423,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02645762873014901,"score_gpt":0.3338192082293743,"score_spread":0.3073615794992253,"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."}}