{"id":"W4328028649","doi":"10.1109/trustcom56396.2022.00098","title":"FLightNER: A Federated Learning Approach to Lightweight Named-Entity Recognition","year":2022,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"Carleton University","funders":"","keywords":"Computer science; Federated learning; Premise; Named-entity recognition; Artificial intelligence; Machine learning; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002998976,0.001211395,0.001290822,0.001361435,0.0006609887,0.001861984,0.003862606,0.001297293,0.003706756],"category_scores_gemma":[0.008035175,0.000596941,0.001552086,0.001400834,0.0006261488,0.005612107,0.002886028,0.002319203,0.00305941],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001057676,"about_ca_system_score_gemma":0.001801208,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009190314,"about_ca_topic_score_gemma":0.01327655,"domain_scores_codex":[0.9985661,0.0002952328,0.0001128072,0.0005902249,0.0003125029,0.0001231701],"domain_scores_gemma":[0.997182,0.0007113632,0.0001346642,0.001408734,0.0004253229,0.0001378964],"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":[0.0007367951,0.0006514921,0.006839169,0.0002575211,0.0003913291,0.0003304796,0.0002540388,0.3445331,0.005688654,0.0125004,0.0526837,0.5751332],"study_design_scores_gemma":[0.00002196697,0.00004660389,0.0003254653,0.00001220449,0.00002223679,0.00007246319,0.00003078884,0.9789098,0.002939371,0.01169846,0.005901095,0.00001949734],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01503061,0.0004684516,0.930419,0.0004639912,0.0001580901,0.0001724069,0.001804011,0.0494929,0.001990494],"genre_scores_gemma":[0.3434137,0.0004089055,0.6310025,0.0008547625,0.000144361,0.0004020803,0.01302064,0.001913983,0.008839101],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.009190314,"threshold_uncertainty_score":0.01827365,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03284144225408836,"score_gpt":0.231483716735156,"score_spread":0.1986422744810677,"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."}}