{"id":"W3032216439","doi":"","title":"Fine-grained Morphosyntactic Analysis and Generation Tools for More Than One Thousand Languages.","year":2020,"lang":"en","type":"article","venue":"Language Resources and Evaluation","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Natural language processing; Security token; Metric (unit); Artificial intelligence; Machine translation; Parallel corpora; Linguistics; Engineering","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":[0.0005583924,0.0001340728,0.0002073218,0.0001276813,0.0001420304,0.0004685094,0.0001884102,0.00007521122,0.0000167004],"category_scores_gemma":[0.0004681106,0.0001147657,0.00005697929,0.0004790295,0.00002987202,0.0004770698,0.00009886998,0.00008376241,7.970229e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002122662,"about_ca_system_score_gemma":0.00001820347,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009388574,"about_ca_topic_score_gemma":0.0001081303,"domain_scores_codex":[0.9988322,0.0000893878,0.0001781606,0.0004052547,0.0003346576,0.0001603962],"domain_scores_gemma":[0.9993278,0.0001341023,0.0001234397,0.0002158447,0.0001082416,0.00009050396],"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":[0.00006270446,0.00004980784,0.002035508,0.0002303308,0.0003725397,0.0000152154,0.04952738,0.0002022818,0.1244705,0.001764563,0.0004601154,0.8208091],"study_design_scores_gemma":[0.0007857814,0.0001873774,0.004536712,0.00003145165,0.0006355745,0.000008360171,0.001018851,0.9554849,0.03605175,0.0006468754,0.0002734444,0.0003388987],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6865679,0.009259092,0.2997341,0.003740316,0.00001460698,0.0004294386,0.00001299404,0.0002002167,0.00004136502],"genre_scores_gemma":[0.8926434,0.00002939947,0.1063689,0.0005751671,0.0001924981,0.0000530411,0.00009771516,0.00001007951,0.00002986701],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9552826,"threshold_uncertainty_score":0.4680008,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04463166772679519,"score_gpt":0.3218636676018755,"score_spread":0.2772319998750803,"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."}}