{"id":"W4403881534","doi":"10.1111/1755-6724.15213","title":"GeoNER: Geological Named Entity Recognition with Enriched Domain Pre‐Training Model and Adversarial Training","year":2024,"lang":"en","type":"article","venue":"Acta Geologica Sinica - English Edition","topic":"Topic Modeling","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Key Research and Development Program of China; National Natural Science Foundation of China; Ministry of Natural Resources","keywords":"Training (meteorology); Adversarial system; Computer science; Domain (mathematical analysis); Training set; Artificial intelligence; Named-entity recognition; Pattern recognition (psychology); Engineering; Mathematics; Geography","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":[0.0009646317,0.001002434,0.0006790428,0.0005133969,0.0002634294,0.0006258109,0.001803316,0.00115431,0.003020886],"category_scores_gemma":[0.00160663,0.0002914003,0.0006619106,0.0005407089,0.0004434397,0.001386709,0.001421798,0.0017459,0.001419462],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005314157,"about_ca_system_score_gemma":0.0006613507,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006104582,"about_ca_topic_score_gemma":0.006338282,"domain_scores_codex":[0.9995893,0.0001071024,0.00001921911,0.0001586944,0.00006549485,0.00006017727],"domain_scores_gemma":[0.9993753,0.000299881,0.00004081768,0.0001482781,0.0001032547,0.00003242058],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002500636,0.0001730052,0.00155927,0.00009299266,0.00009881765,0.0002377987,0.00007032527,0.6887502,0.005918269,0.006550609,0.01119305,0.2851056],"study_design_scores_gemma":[0.000002547187,0.00001729928,0.00009502297,0.000003242982,0.000004701088,0.00001698696,0.000004600603,0.9969689,0.001355607,0.0009938668,0.000533284,0.000003898907],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05614119,0.0009917337,0.928572,0.0007482669,0.0002394406,0.0001146019,0.0007761087,0.007877775,0.004538892],"genre_scores_gemma":[0.795134,0.0004831157,0.1837991,0.0007204587,0.0001449592,0.0002229056,0.003855997,0.0002118879,0.01542763],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006104582,"threshold_uncertainty_score":0.01213813,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04337033694538565,"score_gpt":0.2466242737974124,"score_spread":0.2032539368520268,"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."}}