{"id":"W4366201187","doi":"10.1109/access.2023.3267746","title":"B-NER: A Novel Bangla Named Entity Recognition Dataset With Largest Entities and Its Baseline Evaluation","year":2023,"lang":"en","type":"article","venue":"IEEE Access","topic":"Topic Modeling","field":"Computer Science","cited_by":19,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Named-entity recognition; Computer science; Bengali; Natural language processing; Artificial intelligence; Entity linking; Baseline (sea); Benchmark (surveying); Sentence; F1 score; Task (project management); Information retrieval","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":[0.0009890487,0.00009973947,0.000102233,0.0001437672,0.0001173744,0.0003658441,0.0004621872,0.00003986577,0.00003651746],"category_scores_gemma":[0.00009708526,0.00008999494,0.00001304457,0.0004147856,0.00001655736,0.001715238,0.0001949237,0.00008346474,0.0000580566],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002533956,"about_ca_system_score_gemma":0.00006506914,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001457003,"about_ca_topic_score_gemma":0.000272445,"domain_scores_codex":[0.99879,0.00006192575,0.000157867,0.0003795605,0.0004208974,0.0001897831],"domain_scores_gemma":[0.9993008,0.00007634346,0.00007624374,0.0003113464,0.0001785127,0.00005679722],"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":[0.0002782151,0.001440584,0.03489562,0.001735341,0.0005617611,0.0003105392,0.006149249,0.0272448,0.03500019,0.009792252,0.1353253,0.7472661],"study_design_scores_gemma":[0.0008584109,0.00002788067,0.003170972,0.00006048064,0.00003015056,0.0000131832,0.00001844294,0.9881549,0.005037299,0.001061938,0.001366428,0.0001998503],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6810473,0.00008060684,0.3163335,0.0007661488,0.000583678,0.0003489928,0.0005236822,0.0002063667,0.0001097503],"genre_scores_gemma":[0.9948983,0.0000511452,0.003377145,0.0003314649,0.0001459899,0.00007335427,0.001040647,0.000009418344,0.00007254894],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9609101,"threshold_uncertainty_score":0.3669887,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1369707390250249,"score_gpt":0.3440463260481199,"score_spread":0.207075587023095,"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."}}