{"id":"W2118491422","doi":"10.1007/s10590-004-7693-4","title":"A Morphological Tagger for Korean: Statistical Tagging Combined with Corpus-Based Morphological Rule Application","year":2004,"lang":"en","type":"article","venue":"Machine Translation","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":30,"is_retracted":false,"has_abstract":false,"ca_institutions":"Simon Fraser University","funders":"Social Sciences and Humanities Research Council of Canada; University of Pennsylvania; Yale University","keywords":"Agglutinative language; Computer science; Artificial intelligence; Natural language processing; Lemma (botany); Trigram; Part-of-speech tagging; Part of speech; Component (thermodynamics); Tag system; Rule-based system; Word (group theory); Precision and recall; Computational linguistics; Speech recognition; Linguistics; Parsing; Algorithm; Biology","routes":{"ca_aff":true,"ca_fund":true,"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":[0.002606715,0.001642745,0.001444645,0.003068774,0.001005826,0.002586088,0.002144214,0.001302507,0.009194428],"category_scores_gemma":[0.005729469,0.001502299,0.001239003,0.003511168,0.0006625989,0.003548004,0.00214659,0.001511082,0.01392195],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004765277,"about_ca_system_score_gemma":0.002173773,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001739354,"about_ca_topic_score_gemma":0.003774135,"domain_scores_codex":[0.9985713,0.0003203049,0.0003586714,0.000387969,0.0002776164,0.00008413343],"domain_scores_gemma":[0.9940685,0.00187592,0.0005137195,0.00159202,0.001755396,0.000194548],"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":[0.0006477623,0.000425882,0.004569471,0.001410642,0.0002923441,0.002026009,0.0006909586,0.007575568,0.1689234,0.009498956,0.05038342,0.7535557],"study_design_scores_gemma":[0.0003464982,0.0005225249,0.008789343,0.0002993366,0.0008724215,0.00502225,0.0009232895,0.4045576,0.3822188,0.02779903,0.1681628,0.000486039],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02271048,0.000422714,0.9047409,0.0002822604,0.0003989277,0.0003901769,0.00667253,0.06057926,0.003802694],"genre_scores_gemma":[0.06732234,0.0003689145,0.9075293,0.0002243136,0.00008684397,0.0003159331,0.01480748,0.006024958,0.003319915],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.009194428,"threshold_uncertainty_score":0.03075844,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01525715266378229,"score_gpt":0.2739101294085907,"score_spread":0.2586529767448084,"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."}}