{"id":"W3117829624","doi":"10.48550/arxiv.2012.09936","title":"Named Entity Recognition in the Legal Domain using a Pointer Generator Network","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Topic Modeling","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"Thomson Reuters (Canada)","funders":"","keywords":"Named-entity recognition; Computer science; Pointer (user interface); Security token; Natural language processing; Task (project management); Artificial intelligence; Annotation; Information retrieval; Computer security","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":[0.001005817,0.0005286587,0.0004097551,0.0008643241,0.0005097344,0.0007333184,0.001281191,0.001290987,0.002938899],"category_scores_gemma":[0.003375007,0.0003135961,0.0006247998,0.0009151585,0.0005723581,0.002385922,0.0009817535,0.001345627,0.001388902],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008389186,"about_ca_system_score_gemma":0.0007095994,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005595183,"about_ca_topic_score_gemma":0.007967469,"domain_scores_codex":[0.9997,0.00008009734,0.00001526317,0.0001250764,0.00004822058,0.00003140533],"domain_scores_gemma":[0.9989455,0.0006250558,0.00006127232,0.0001476109,0.0001842102,0.00003626894],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0002357319,0.0003241229,0.003001838,0.0001431033,0.00008858873,0.0005946968,0.0002502482,0.4976459,0.01571451,0.01866281,0.01488569,0.4484527],"study_design_scores_gemma":[0.00000738608,0.00002407752,0.0002702818,0.000007308402,0.00000883018,0.00003728937,0.0000150511,0.9895359,0.003128806,0.005901135,0.00105703,0.000006854794],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.109157,0.0006172194,0.8733625,0.001357959,0.0001927466,0.0001811261,0.001005328,0.007559154,0.006566899],"genre_scores_gemma":[0.6158429,0.0005041257,0.3645454,0.0005170807,0.0001542544,0.000289519,0.004216098,0.0002824697,0.01364811],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005595183,"threshold_uncertainty_score":0.01112521,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1292033761029976,"score_gpt":0.1975703471031332,"score_spread":0.06836697100013561,"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."}}