{"id":"W3200172683","doi":"10.18653/v1/2021.emnlp-main.516","title":"Mind the Context: The Impact of Contextualization in Neural Module Networks for Grounding Visual Referring Expressions","year":2021,"lang":"en","type":"article","venue":"Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing","topic":"Multimodal Machine Learning Applications","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Contextualization; Computer science; Generalization; Context (archaeology); Set (abstract data type); Exploit; Parameterized complexity; Artificial intelligence; Test set; Embedding; Cube (algebra); Machine learning; Algorithm; Mathematics; Programming language","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":[0.001587611,0.0002182813,0.0003717706,0.0001176688,0.0002577488,0.0002222773,0.001260813,0.0001150902,0.000008913917],"category_scores_gemma":[0.003504386,0.0001124176,0.0001769391,0.001443013,0.0001589965,0.0003570558,0.0004782177,0.0008295822,1.915006e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001106192,"about_ca_system_score_gemma":0.0001522618,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001790519,"about_ca_topic_score_gemma":0.00003143307,"domain_scores_codex":[0.9980257,0.000286964,0.000576772,0.0004634743,0.0002991046,0.0003480055],"domain_scores_gemma":[0.9972944,0.001368234,0.0005339389,0.0002793272,0.0004793116,0.00004482003],"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":[0.00008803403,0.0001887376,0.01570872,0.000107182,0.00002704742,0.000001112276,0.01397472,0.004712285,0.08177587,0.006997934,0.0000185534,0.8763998],"study_design_scores_gemma":[0.000366586,0.00004520221,0.03191762,0.0004655492,0.00001148016,0.000008360422,0.002586969,0.9513921,0.01176837,0.001292449,0.000006796859,0.000138557],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7771295,0.002388463,0.2157785,0.003402621,0.0001741653,0.0007532968,0.000003456631,0.00002680726,0.0003431587],"genre_scores_gemma":[0.9409637,0.000007461574,0.05866545,0.0001541181,0.0000585635,0.00008852058,0.000002125423,0.00001494994,0.00004506943],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9466798,"threshold_uncertainty_score":0.4584257,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06160955148695172,"score_gpt":0.4607618939277148,"score_spread":0.399152342440763,"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."}}