{"id":"W4385573873","doi":"10.18653/v1/2022.emnlp-main.586","title":"Contrastive Learning with Expectation-Maximization for Weakly Supervised Phrase Grounding","year":2022,"lang":"en","type":"article","venue":"","topic":"Multimodal Machine Learning Applications","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa","funders":"Fundamental Research Funds for the Central Universities; State Key Laboratory of Software Development Environment; Leverhulme Trust","keywords":"Phrase; Computer science; Margin (machine learning); Artificial intelligence; Annotation; Object (grammar); Natural language processing; Perspective (graphical); Expectation–maximization algorithm; Maximization; Pattern recognition (psychology); Speech recognition; Machine learning; Maximum likelihood; Mathematics","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":[0.004219806,0.002476459,0.002246141,0.001440553,0.0006910425,0.001428587,0.004163227,0.002925416,0.00356431],"category_scores_gemma":[0.01176789,0.0009353604,0.001498799,0.001458612,0.001931475,0.003423283,0.00283606,0.003969185,0.002413918],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001340144,"about_ca_system_score_gemma":0.001296472,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002176324,"about_ca_topic_score_gemma":0.003257185,"domain_scores_codex":[0.9973707,0.00109883,0.0001089291,0.0008672469,0.0003697331,0.0001844792],"domain_scores_gemma":[0.9945352,0.003666067,0.0003536908,0.0006903448,0.0005681032,0.0001866401],"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":[0.0009509607,0.0005599298,0.002681623,0.0005716382,0.0003197609,0.0003843287,0.0003390117,0.455482,0.01999182,0.0198564,0.01563417,0.4832284],"study_design_scores_gemma":[0.00003068037,0.0000819537,0.0001938232,0.00001262006,0.00001611307,0.00004193485,0.00001601979,0.9842741,0.002820978,0.01180896,0.0006891611,0.00001363716],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01145272,0.0003665107,0.9844796,0.0002581355,0.00004043934,0.00007960902,0.0001866223,0.002219272,0.0009171449],"genre_scores_gemma":[0.4600676,0.0004047572,0.5287865,0.001181002,0.0003186051,0.0005412465,0.002590919,0.001018329,0.005091059],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004219806,"threshold_uncertainty_score":0.02231669,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.008977920109588727,"score_gpt":0.2370852657185742,"score_spread":0.2281073456089855,"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."}}