{"id":"W4385571080","doi":"10.18653/v1/2023.acl-long.508","title":"Grounded Multimodal Named Entity Recognition on Social Media","year":2023,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":33,"is_retracted":false,"has_abstract":true,"ca_institutions":"Fields Institute for Research in Mathematical Sciences","funders":"Government of Jiangsu Province; Natural Science Foundation of Jiangsu Province; National Natural Science Foundation of China","keywords":"Computer science; Baseline (sea); Task (project management); Construct (python library); Entity linking; Artificial intelligence; Bounding overwatch; Information retrieval; Named-entity recognition; Social media; Natural language processing; Index (typography); Graph; World Wide Web; Knowledge base; Theoretical computer science","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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0002236335,0.00006574883,0.00007476885,0.0000895991,0.0001151411,0.00008562358,0.0002978584,0.00005351135,0.00006122524],"category_scores_gemma":[0.00009099735,0.0000622439,0.00004359659,0.0002736922,0.00001377146,0.0002350784,0.0001219062,0.00008988132,0.00116664],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003695792,"about_ca_system_score_gemma":0.00002179621,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005785596,"about_ca_topic_score_gemma":0.0000852236,"domain_scores_codex":[0.9991394,0.00004093128,0.000116664,0.0002565373,0.0002571235,0.0001893589],"domain_scores_gemma":[0.999595,0.0001266794,0.00002694209,0.0001726824,0.00003725238,0.00004141543],"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":[0.000007672845,0.00008185946,0.0000841529,0.0000102526,0.0000125929,0.00002072951,0.002982724,0.00004323634,0.000552158,0.05531779,0.004634377,0.9362525],"study_design_scores_gemma":[0.001279766,0.00003359055,0.02117143,0.00001634825,0.000005512497,0.000003005166,0.0002179722,0.8684393,0.002428339,0.1051606,0.00086225,0.0003818776],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6084982,0.000001812864,0.3750297,0.002251019,0.001548504,0.0001221982,0.000003109405,0.001192563,0.01135292],"genre_scores_gemma":[0.9826509,0.000002771411,0.01650296,0.0002736943,0.0002533183,0.00001113159,0.00001278537,0.000004875043,0.0002875144],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9358706,"threshold_uncertainty_score":0.9996111,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1015538905006703,"score_gpt":0.2899108478936894,"score_spread":0.1883569573930191,"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."}}