{"id":"W4415427950","doi":"10.3233/faia251357","title":"Enhancing Few Shot Named Entity Recognition via Label Semantic Description and Diversity Text","year":2025,"lang":"","type":"book-chapter","venue":"Frontiers in artificial intelligence and applications","topic":"Topic Modeling","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Entity linking; Named-entity recognition; Semantic similarity; Context (archaeology); Representation (politics); Semantics (computer science); Semantic role labeling; Generative grammar","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":[0.0006095081,0.0004403749,0.0005459121,0.000598188,0.001183599,0.0003909208,0.0006047808,0.000432276,0.00004833494],"category_scores_gemma":[0.00004939231,0.0005544841,0.00009359032,0.0003759517,0.0004347786,0.0006346108,0.00102558,0.0006554547,0.0000524007],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001983153,"about_ca_system_score_gemma":0.0001036678,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004581377,"about_ca_topic_score_gemma":0.0008376187,"domain_scores_codex":[0.9968221,0.00007029173,0.0009698632,0.001365645,0.0003317519,0.0004404038],"domain_scores_gemma":[0.998503,0.0001147017,0.0003398774,0.0006246667,0.0002369046,0.0001808433],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00002029439,0.0001171984,0.0005341177,0.0001809441,0.00004271241,0.000003721452,0.0009854732,0.00004250387,0.0003755405,0.07972544,0.00004216826,0.9179299],"study_design_scores_gemma":[0.00007962155,0.00007082632,0.00009829933,0.0007310569,0.0001790333,0.000008379137,0.0006897051,0.3258488,0.002536178,0.6671954,0.001813822,0.0007488478],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002351064,0.001488405,0.9905226,0.000424832,0.0009411768,0.001328444,0.00003498627,0.00006888322,0.002839588],"genre_scores_gemma":[0.8094197,0.01150597,0.1723287,0.000435502,0.0005563173,0.0003020189,0.0001040795,0.0000437511,0.005303933],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.917181,"threshold_uncertainty_score":0.9996907,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08487523840846307,"score_gpt":0.273667627722973,"score_spread":0.18879238931451,"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."}}