{"id":"W4382542296","doi":"10.1017/s1351324923000311","title":"Korean named entity recognition based on language-specific features","year":2023,"lang":"en","type":"article","venue":"Natural Language Engineering","topic":"Topic Modeling","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Morpheme; Natural language processing; Artificial intelligence; Annotation; Named-entity recognition; Scheme (mathematics); Ambiguity; Segmentation; Syllable; Word (group theory); Speech recognition; Task (project management); Linguistics","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":[],"consensus_categories":[],"category_scores_codex":[0.00020739,0.0001617504,0.0001285578,0.0002825566,0.00005891927,0.000122997,0.0004286582,0.0000798049,0.00002431465],"category_scores_gemma":[0.0001345445,0.0001508163,0.00007858888,0.0005681364,0.000006560717,0.0002165292,0.00008662326,0.0003828743,0.0001524727],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007175589,"about_ca_system_score_gemma":0.00001188084,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003144908,"about_ca_topic_score_gemma":0.000006835694,"domain_scores_codex":[0.9988479,0.00002420155,0.0001346757,0.0003487282,0.0003175502,0.0003269618],"domain_scores_gemma":[0.9992962,0.0001234111,0.00003138888,0.0004502186,0.0000283288,0.00007048326],"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":[0.00002699285,0.00005997219,0.000097923,0.0001744691,0.00004324383,0.001118428,0.007662422,0.084861,0.09505205,0.003434421,0.003763651,0.8037055],"study_design_scores_gemma":[0.0003322688,0.00002084905,0.00204235,0.00008682072,0.000003142009,0.00001003488,0.0001259194,0.9781904,0.01837987,0.00002608866,0.0004927356,0.0002895446],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8169062,0.002256067,0.1709915,0.0007475733,0.003391508,0.0003580658,0.00002165282,0.00405666,0.001270837],"genre_scores_gemma":[0.9767797,0.000006706117,0.02235509,0.0001599062,0.0002947002,0.00001290851,0.00006725384,0.00002012875,0.0003036273],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8933294,"threshold_uncertainty_score":0.6150112,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01003904351749246,"score_gpt":0.2231050327943933,"score_spread":0.2130659892769008,"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."}}