{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003872894,0.0002766205,0.0004451923,0.0003080092,0.00007894611,0.0001588371,0.0007635658,0.0001712189,0.00001441052],"category_scores_gemma":[0.00003092082,0.0003191305,0.00005687469,0.0006771121,0.00008199995,0.000355639,0.002843511,0.0009758667,0.00004783872],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001945567,"about_ca_system_score_gemma":0.0001395335,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003029092,"about_ca_topic_score_gemma":0.003338887,"domain_scores_codex":[0.9974455,0.0005749886,0.0002491303,0.001379467,0.0001077455,0.0002432295],"domain_scores_gemma":[0.9985595,0.0002527501,0.0001452679,0.0006752136,0.0002629126,0.0001042989],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0005882728,0.003039584,0.4936456,0.001219986,0.001032485,0.005145805,0.0224247,0.3010626,0.0000166943,0.0667932,0.000432227,0.1045989],"study_design_scores_gemma":[0.001602284,0.0002199631,0.07669216,0.0003967677,0.00007765603,0.000008549799,0.002404693,0.7941893,0.00002151404,0.1218625,0.001464786,0.001059895],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9635044,0.002912559,0.03073265,0.00005353369,0.000877226,0.0006900572,0.00003060444,0.0001343438,0.001064598],"genre_scores_gemma":[0.9961326,0.00306632,0.0005952361,0.00003876991,0.00002969322,0.000003077699,0.0000175246,0.000006939545,0.0001098338],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4931267,"threshold_uncertainty_score":0.9999261,"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."}}