{"id":"W4391124783","doi":"10.48550/arxiv.2401.10825","title":"Recent Advances in Named Entity Recognition: A Comprehensive Survey and Comparative Study","year":2024,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Topic Modeling","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":true,"ca_institutions":"Collège Boréal","funders":"","keywords":"Substring; Computer science; Implementation; Variety (cybernetics); Artificial intelligence; Transformer; Data science; Named-entity recognition; Graph; Natural language processing; Machine learning; Data structure; Theoretical computer science; Task (project management); Software engineering","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":[0.009783936,0.002387508,0.00332248,0.01313005,0.001067664,0.003921216,0.00354442,0.001749859,0.004598471],"category_scores_gemma":[0.02583245,0.001096065,0.002087939,0.02127384,0.001366035,0.01651581,0.003385229,0.002869097,0.005792514],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00123761,"about_ca_system_score_gemma":0.002239559,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003020853,"about_ca_topic_score_gemma":0.003190096,"domain_scores_codex":[0.9943539,0.001471131,0.0006258874,0.001841843,0.001458263,0.000248994],"domain_scores_gemma":[0.9695285,0.02185007,0.001033964,0.003144824,0.003942135,0.0005005846],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001567031,0.0001429986,0.00576654,0.006712139,0.0002964766,0.0001198751,0.0003493591,0.005798917,0.001149898,0.01029948,0.03951752,0.92969],"study_design_scores_gemma":[0.00003802552,0.0003306686,0.01611681,0.003918412,0.0009050245,0.001950937,0.001569563,0.06037314,0.007468532,0.03845015,0.8685772,0.000301595],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.01277038,0.7925653,0.1681152,0.004640418,0.001863627,0.0001747755,0.002908888,0.00288621,0.0140752],"genre_scores_gemma":[0.06930509,0.7634975,0.1362948,0.002503219,0.005618832,0.00019785,0.01697406,0.0009899074,0.004618682],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.01313005,"threshold_uncertainty_score":0.05174303,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2442692213471044,"score_gpt":0.2589056125410715,"score_spread":0.01463639119396706,"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."}}