{"id":"W3001286655","doi":"10.17605/osf.io/n9pmd","title":"Inter-rater reliability for study selection of Spanish language articles using Google’s Neural Machine Translation (Google Translate)","year":2020,"lang":"en","type":"article","venue":"OSF Preprints (OSF Preprints)","topic":"Educational Technology and Assessment","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Machine translation; Selection (genetic algorithm); Natural language processing; Computer science; Reliability (semiconductor); Artificial intelligence; Inter-rater reliability; Information retrieval; Machine learning; Statistics; Mathematics","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.3502807,0.001367147,0.003902335,0.01316245,0.002445584,0.004418974,0.001766924,0.001735077,0.003349188],"category_scores_gemma":[0.6177743,0.001282685,0.006703244,0.008401644,0.003677972,0.003562408,0.005604067,0.001712477,0.002040756],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001735596,"about_ca_system_score_gemma":0.004007131,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002008652,"about_ca_topic_score_gemma":0.004780331,"domain_scores_codex":[0.5789097,0.2564924,0.09636591,0.0235396,0.04219109,0.002501278],"domain_scores_gemma":[0.2425181,0.4947108,0.05645289,0.06329446,0.1403705,0.002653171],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0120815,0.0008752603,0.5997725,0.03464977,0.0259345,0.001284825,0.06838106,0.005019268,0.01379608,0.009531899,0.0243092,0.2043643],"study_design_scores_gemma":[0.003846903,0.003479844,0.7056186,0.01640503,0.02387454,0.003358347,0.01921904,0.059095,0.02971211,0.02452189,0.1092626,0.001606185],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6942255,0.02560705,0.2052763,0.0032388,0.003937327,0.02694208,0.01506866,0.001940317,0.02376389],"genre_scores_gemma":[0.8526195,0.002396441,0.1063023,0.0007194381,0.000602423,0.02829338,0.006371963,0.0008493411,0.001845175],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6497193,"threshold_uncertainty_score":0.8012196,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03353334232358544,"score_gpt":0.316249793916117,"score_spread":0.2827164515925315,"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."}}