{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003009971,0.0002095995,0.0002234317,0.0001001223,0.0001632889,0.0001060173,0.0004315226,0.0001271923,0.00001158155],"category_scores_gemma":[0.000038572,0.000151047,0.000054133,0.0003136196,0.00009764548,0.0002479966,0.00002382593,0.0002206056,0.000007129286],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006555772,"about_ca_system_score_gemma":0.0000589561,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005617363,"about_ca_topic_score_gemma":0.00001940447,"domain_scores_codex":[0.9985995,0.00005055646,0.0002627985,0.0005143104,0.000288474,0.0002843444],"domain_scores_gemma":[0.9992096,0.0001784748,0.0001125366,0.0003229566,0.0000911909,0.00008522374],"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":[0.001734573,0.001114456,0.001840384,0.0001958808,0.00004153774,0.0002807137,0.0003996064,0.008202186,0.07013679,0.400562,0.0001429542,0.5153489],"study_design_scores_gemma":[0.006248585,0.002021578,0.002035445,0.00007478643,0.00005714041,0.0001785538,0.000003882801,0.7244746,0.03929426,0.2241314,0.0007057575,0.0007739685],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.007536123,0.0002916117,0.9866029,0.003757202,0.00003165817,0.0007753949,0.00003528237,0.0009107676,0.00005905808],"genre_scores_gemma":[0.5077358,9.514543e-7,0.4915412,0.0004172364,0.00001590896,0.0001209758,0.0001549563,0.00000993695,0.0000029749],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7162724,"threshold_uncertainty_score":0.6159517,"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."}}