{"id":"W2250595697","doi":"","title":"Building NLP resources for Dzongkha: A Tagset and A Tagged Corpus","year":2010,"lang":"en","type":"article","venue":"Publication Server of the Institute for German Language (Institute for German Language)","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National University of Computer and Emerging Sciences; Universität Stuttgart; International Development Research Centre","keywords":"Treebank; Lexicon; Computer science; Natural language processing; Artificial intelligence; Set (abstract data type); Security token; Part of speech; Word (group theory); Training set; Speech recognition; Parsing; Linguistics","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001193241,0.0004766973,0.0005389777,0.0004121966,0.0006975777,0.0005661013,0.002857528,0.0003167512,0.00001042862],"category_scores_gemma":[0.001081838,0.0003805823,0.0003954492,0.0006935789,0.0004561022,0.002513378,0.0006482822,0.0004138739,0.000002628889],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008700676,"about_ca_system_score_gemma":0.0002197205,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005971832,"about_ca_topic_score_gemma":0.001682639,"domain_scores_codex":[0.9971274,0.00004723572,0.00077981,0.0009020115,0.0004722336,0.0006713113],"domain_scores_gemma":[0.9962696,0.00022795,0.000832011,0.001762298,0.0006919628,0.0002161704],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0002274355,0.0003012294,0.000174482,0.00163399,0.0002506416,0.00001246847,0.01446521,0.00003842224,0.3115171,0.5884936,0.01420664,0.06867865],"study_design_scores_gemma":[0.006226506,0.0004161788,0.001123712,0.0005585204,0.0004082088,0.0003980579,0.0002533893,0.02024755,0.3852357,0.03382402,0.5489811,0.002326976],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5902312,0.00171953,0.3953507,0.004613765,0.001868643,0.004083509,0.001114801,0.0009029874,0.0001147942],"genre_scores_gemma":[0.5655025,0.000006343548,0.4302974,0.001076533,0.0005403295,0.0009542905,0.0004433467,0.00006207462,0.001117203],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5546697,"threshold_uncertainty_score":0.9998646,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0109800960401046,"score_gpt":0.2980911649840398,"score_spread":0.2871110689439352,"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."}}