{"id":"W4407639229","doi":"10.1109/bip63158.2024.10885387","title":"Relation Extraction from Unstructured Species Descriptions Using TaxonNERD and Llama 7B","year":2024,"lang":"en","type":"article","venue":"","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Ministerio de Ciencia Tecnología y Telecomunicaciones; Instituto Tecnológico de Costa Rica; Consejo Superior Universitario Centroamericano; International Development Research Centre","keywords":"Relation (database); Computer science; Extraction (chemistry); Relationship extraction; Data mining; Chromatography; Chemistry","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001998533,0.001312792,0.0008837533,0.01061116,0.001175443,0.002430995,0.001104399,0.001212012,0.004892256],"category_scores_gemma":[0.009183114,0.0006443721,0.0020459,0.005838688,0.0005067089,0.003508878,0.002539569,0.001079694,0.002880567],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001535545,"about_ca_system_score_gemma":0.002511473,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01503297,"about_ca_topic_score_gemma":0.03439524,"domain_scores_codex":[0.9984506,0.0003246068,0.0003873577,0.0003951314,0.0003703649,0.00007189635],"domain_scores_gemma":[0.9965347,0.001905429,0.0003846142,0.000597361,0.0004692372,0.0001085974],"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":[0.0008786928,0.0006122622,0.05679515,0.008162904,0.0008874258,0.003250615,0.00436327,0.0270529,0.03503184,0.03976779,0.1419825,0.6812146],"study_design_scores_gemma":[0.0002061465,0.0001673212,0.02990505,0.001159935,0.0003705615,0.002466693,0.002178954,0.3318225,0.0293528,0.04031582,0.5618592,0.0001949782],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.08346624,0.004912752,0.5509178,0.002292179,0.0003698397,0.002131585,0.2715535,0.07135947,0.01299667],"genre_scores_gemma":[0.09102784,0.001133644,0.6765884,0.0003552574,0.00003955751,0.001156005,0.2263884,0.0009015947,0.002409441],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01503297,"threshold_uncertainty_score":0.02989095,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03603538874174903,"score_gpt":0.2889795448439157,"score_spread":0.2529441561021666,"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."}}