{"id":"W2460844011","doi":"10.7202/1036327ar","title":"A Methodology for Multilingual Automatic Item Generation","year":2016,"lang":"en","type":"article","venue":"Mesure et évaluation en éducation","topic":"Educational Technology and Assessment","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Item bank; Task (project management); Test (biology); Process (computing); Quality (philosophy); Item response theory; Natural language processing; Multilingualism; Artificial intelligence; Information retrieval; Psychometrics; Psychology; Programming language","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":true,"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":[0.01363476,0.00210314,0.0012484,0.005326106,0.001713903,0.002360751,0.002782343,0.001415063,0.01358883],"category_scores_gemma":[0.04312292,0.001471751,0.001844829,0.003911681,0.001547345,0.002258785,0.003944202,0.002779698,0.005862962],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001202622,"about_ca_system_score_gemma":0.00211906,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001965464,"about_ca_topic_score_gemma":0.002747438,"domain_scores_codex":[0.979839,0.01160552,0.001497565,0.002422444,0.00431409,0.0003213742],"domain_scores_gemma":[0.9726706,0.01484004,0.0009341497,0.004499326,0.006763665,0.0002922549],"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":[0.0002139218,0.0002004025,0.001532514,0.0004461719,0.0001750626,0.0003474278,0.001290418,0.01398098,0.009334018,0.03972405,0.009302333,0.9234527],"study_design_scores_gemma":[0.0005781482,0.0006470504,0.004069804,0.0004421347,0.0002375164,0.002709418,0.0008709515,0.6114954,0.04254889,0.1926337,0.1433472,0.0004198305],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0004898494,0.000030855,0.9972057,0.00003641764,0.00001850134,0.0002556232,0.00007749908,0.001402816,0.0004827708],"genre_scores_gemma":[0.00860613,0.00002676425,0.9892201,0.00003826796,0.00001537078,0.0007844577,0.0003074259,0.0002680212,0.0007334648],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01363476,"threshold_uncertainty_score":0.07210845,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2404719341550069,"score_gpt":0.4683928688355242,"score_spread":0.2279209346805173,"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."}}