{"id":"W4323649518","doi":"10.23977/acss.2023.070111","title":"Research on Named Entity Recognition Method Based on Language Pre-Training Model","year":2023,"lang":"en","type":"article","venue":"Advances in Computer Signals and Systems","topic":"Topic Modeling","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Computer science; Word (group theory); Representation (politics); Polysemy; Artificial intelligence; Word embedding; Set (abstract data type); Vectorization (mathematics); Natural language processing; Embedding; Language model; Training set; Support vector machine; Data set; Machine learning; Data mining; Mathematics","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003207127,0.0001385511,0.0002479913,0.0004598841,0.0001349591,0.0002278611,0.0004441298,0.00007225109,0.000001326371],"category_scores_gemma":[0.00003922207,0.0001246555,0.00003744185,0.0006286617,0.00002413036,0.0004134486,0.0001538987,0.0002829053,0.00002111576],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004965116,"about_ca_system_score_gemma":0.00004510736,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005031496,"about_ca_topic_score_gemma":0.00001200961,"domain_scores_codex":[0.9974945,0.0006021819,0.0003172106,0.0006276071,0.0005626866,0.0003958508],"domain_scores_gemma":[0.9982608,0.001070486,0.00007323806,0.0004347651,0.00008012383,0.0000806043],"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":[0.000008921425,0.00002183487,0.00004183672,0.00006992844,0.00000281312,0.00002460777,0.001460249,0.7737026,0.0001135479,0.002173192,0.00003893752,0.2223415],"study_design_scores_gemma":[0.0003083766,0.000145028,0.00006202061,0.0004267379,8.931829e-7,0.000002954205,0.0001413721,0.9946245,0.0001633489,0.003856587,0.0001267005,0.0001415029],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04769678,0.0003337801,0.9500977,0.000144136,0.0005735013,0.0003147554,0.00000596602,0.0001750047,0.0006583311],"genre_scores_gemma":[0.9015135,0.00005567814,0.09788357,0.000185114,0.0001970348,0.00008040504,0.00000717638,0.00001161873,0.00006597154],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8538166,"threshold_uncertainty_score":0.5083305,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1624838725008738,"score_gpt":0.423410809705627,"score_spread":0.2609269372047532,"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."}}