{"id":"W4385570797","doi":"10.18653/v1/2023.findings-acl.414","title":"K-UniMorph: Korean Universal Morphology and its Feature Schema","year":2023,"lang":"en","type":"article","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"University of British Columbia; National Research Foundation of Korea; National Research Foundation","keywords":"Computer science; Natural language processing; Artificial intelligence; Inflection; Morpheme; Verb; Schema (genetic algorithms); Feature (linguistics); Linguistics; Information retrieval","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":[0.0006842751,0.001201159,0.0006373398,0.003972917,0.001053112,0.001483074,0.00233168,0.001179899,0.008673841],"category_scores_gemma":[0.002453914,0.0004290667,0.001122553,0.005097526,0.0006378842,0.002269354,0.002168088,0.001107589,0.009081094],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009717668,"about_ca_system_score_gemma":0.001542168,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006388935,"about_ca_topic_score_gemma":0.01497762,"domain_scores_codex":[0.999109,0.00009428479,0.0001842575,0.0002912538,0.0002030921,0.0001181305],"domain_scores_gemma":[0.9982437,0.0002013193,0.0002064339,0.0006885916,0.0004660915,0.0001938398],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.001197175,0.0007447514,0.05133291,0.004247204,0.0002208996,0.001761418,0.001459224,0.003895705,0.02784158,0.01623711,0.6811931,0.209869],"study_design_scores_gemma":[0.000159192,0.0001765488,0.05671787,0.0002367856,0.000084885,0.002080119,0.001491293,0.005695747,0.01384292,0.004518548,0.9148721,0.0001239731],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"methods","genre_scores_codex":[0.07715174,0.0007082314,0.009038731,0.0002929322,0.0001816677,0.0003305548,0.8936418,0.00600813,0.01264617],"genre_scores_gemma":[0.02993711,0.0001628771,0.01354449,0.0001100563,0.000013866,0.000407257,0.9532249,0.0003398934,0.002259463],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.008673841,"threshold_uncertainty_score":0.02901691,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01478005177857646,"score_gpt":0.2621955323836276,"score_spread":0.2474154806050511,"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."}}