{"id":"W4376166979","doi":"10.1145/3539618.3591852","title":"Extracting Complex Named Entities in Legal Documents via Weakly Supervised Object Detection","year":2023,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Thomson Reuters (Canada)","funders":"","keywords":"Computer science; Dependency (UML); Named-entity recognition; Artificial intelligence; Object (grammar); Information retrieval; Baseline (sea); Information extraction; Object detection; Natural language processing; Data mining; Machine learning; Pattern recognition (psychology); Task (project management)","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":[0.0003666935,0.0001057542,0.0001243683,0.0002533013,0.0001106616,0.0002384884,0.0004129872,0.00004467108,0.0000781917],"category_scores_gemma":[0.00003672281,0.0001066781,0.00004443348,0.0005426572,0.00001285734,0.0009776743,0.000222841,0.0001383116,0.0001640397],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008029938,"about_ca_system_score_gemma":0.00002959259,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001784622,"about_ca_topic_score_gemma":0.001027791,"domain_scores_codex":[0.9987376,0.00006630019,0.0002596552,0.0003346766,0.0002776489,0.0003241507],"domain_scores_gemma":[0.9994857,0.00008649351,0.00004113592,0.0003106583,0.0000298725,0.00004610168],"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":[0.0000268687,0.0001379718,0.01047156,0.00011742,0.00005414689,0.0002142084,0.006693624,0.009399288,0.3129793,0.01698167,0.0006039809,0.6423199],"study_design_scores_gemma":[0.0003288368,0.00002320522,0.01125198,0.00001537492,0.00000151778,0.00001255701,0.0002974308,0.9779525,0.007421705,0.001601543,0.000932482,0.0001608746],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5177294,0.000008425833,0.4753082,0.0003242232,0.0005529196,0.0001301993,2.505628e-7,0.0004916344,0.005454775],"genre_scores_gemma":[0.9859619,0.000004342921,0.01219492,0.0001150996,0.00005738964,0.00001748805,0.000002078406,0.000007856715,0.001638992],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9685532,"threshold_uncertainty_score":0.4350207,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03620104001552275,"score_gpt":0.2766151920168823,"score_spread":0.2404141520013596,"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."}}