{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001061351,0.0006478449,0.0006658632,0.001207068,0.0002925924,0.001009352,0.0009313821,0.0005183435,0.001617413],"category_scores_gemma":[0.002474282,0.0001883506,0.0008842655,0.001480123,0.000253569,0.003891006,0.0006673241,0.0006798471,0.001289908],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003224537,"about_ca_system_score_gemma":0.000385711,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003517365,"about_ca_topic_score_gemma":0.0050681,"domain_scores_codex":[0.9993898,0.0001613372,0.00005693959,0.0002323803,0.0001051049,0.0000544218],"domain_scores_gemma":[0.998647,0.0004862421,0.0001237759,0.0003296444,0.0003699043,0.00004335548],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0005904056,0.0002498176,0.01550482,0.0003344833,0.0003655965,0.0004507175,0.0002859675,0.1545227,0.06398987,0.008916793,0.006826218,0.7479627],"study_design_scores_gemma":[0.000007149756,0.00005276056,0.004027413,0.00001622231,0.00009007432,0.0001378311,0.00007113719,0.964128,0.02601821,0.001780527,0.003634497,0.00003616003],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1557474,0.0008731891,0.8316519,0.0002788003,0.0001731523,0.0001065028,0.001078384,0.005788933,0.004301824],"genre_scores_gemma":[0.7500292,0.0005328913,0.2423421,0.00008902161,0.00004631277,0.00006321108,0.003723466,0.0001840015,0.0029897],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003517365,"threshold_uncertainty_score":0.006993771,"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."}}