{"id":"W3029286378","doi":"10.3929/ethz-b-000462327","title":"UniMorph 3.0: Universal Morphology","year":2020,"lang":"en","type":"article","venue":"Minerva Access (University of Melbourne)","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":54,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Unimorph; Computer science; Schema (genetic algorithms); Annotation; Artificial intelligence; Natural language processing; Software engineering; Information retrieval","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":[0.0001138766,0.0001365988,0.0002491703,0.0001529557,0.000137646,0.00006338674,0.003310959,0.0001120885,0.000156715],"category_scores_gemma":[0.00004565472,0.0001558676,0.00009099335,0.0007902776,0.0001510944,0.001647108,0.001304843,0.0002194321,0.00002761954],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004001436,"about_ca_system_score_gemma":0.000093468,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004845488,"about_ca_topic_score_gemma":0.00003469693,"domain_scores_codex":[0.9989705,0.00007054688,0.0001101043,0.0003784827,0.0002355324,0.0002348455],"domain_scores_gemma":[0.9991005,0.00004734472,0.0001802275,0.000342678,0.0001626513,0.0001665817],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0004400366,0.0004795299,0.0115026,0.0006097089,0.0003677247,0.005615597,0.02144395,0.0003137416,0.2024084,0.3461463,0.117255,0.2934174],"study_design_scores_gemma":[0.01690773,0.003277114,0.02896287,0.0009060894,0.0006649915,0.0009172249,0.008752102,0.3663233,0.2570136,0.1096516,0.1990564,0.007566966],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09763742,0.000562307,0.8799047,0.0190961,0.0001048987,0.0001220722,0.000006218118,0.0005636216,0.002002684],"genre_scores_gemma":[0.7602729,0.00002916969,0.2384863,0.0006739332,0.00004077193,8.343801e-8,0.000004007502,0.000008111462,0.0004848062],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6626354,"threshold_uncertainty_score":0.6356095,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03029680250246535,"score_gpt":0.2431710628218441,"score_spread":0.2128742603193787,"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."}}