{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000283938,0.0007329209,0.0003785406,0.000624739,0.0002239434,0.001201048,0.0009481388,0.0006300471,0.008599402],"category_scores_gemma":[0.004223855,0.0002903089,0.0005027482,0.0005962154,0.0006161327,0.005129055,0.001888899,0.0007727974,0.001388285],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004186799,"about_ca_system_score_gemma":0.000311578,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002573983,"about_ca_topic_score_gemma":0.003464591,"domain_scores_codex":[0.9997525,0.00005115461,0.0000113947,0.0001076463,0.00004365029,0.00003362742],"domain_scores_gemma":[0.9993355,0.0002701594,0.00009642572,0.0001686025,0.00005750533,0.00007178925],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00100512,0.0003808852,0.008939539,0.0006588143,0.0001443113,0.0007809811,0.002767408,0.01902595,0.2153183,0.03560595,0.01593901,0.6994338],"study_design_scores_gemma":[0.00008745657,0.0008498036,0.02204155,0.000153198,0.0001575339,0.0009137291,0.001432748,0.6773905,0.1127078,0.1567157,0.02740105,0.0001489225],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.34384,0.0007595067,0.6271536,0.0009182571,0.0001618261,0.000253294,0.002225237,0.01034453,0.01434375],"genre_scores_gemma":[0.8642973,0.0002177311,0.1289341,0.0002050466,0.00003804755,0.0001113568,0.001772601,0.0003426848,0.004081214],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.008599402,"threshold_uncertainty_score":0.02876788,"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."}}