{"id":"W4200387115","doi":"10.18280/ria.350609","title":"Automatic Short Answer Grading System in Indonesian Language Using BERT Machine Learning","year":2021,"lang":"en","type":"article","venue":"Revue d intelligence artificielle","topic":"Edcuational Technology Systems","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Computer science; Confusion matrix; Confusion; Grading (engineering); Artificial intelligence; Natural language processing; Indonesian; Machine learning; Engineering; Linguistics","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007712021,0.0001840905,0.0003130339,0.0003153927,0.0001760439,0.0001306516,0.0006703391,0.0001381085,0.00003099953],"category_scores_gemma":[0.0002008358,0.0002002538,0.00008196969,0.001467633,0.00005018176,0.0003299814,0.0002533068,0.0003819204,0.0001363303],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002446036,"about_ca_system_score_gemma":0.00008974599,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001518195,"about_ca_topic_score_gemma":0.0001127051,"domain_scores_codex":[0.9979524,0.0002063734,0.0006192786,0.0005623887,0.000262124,0.0003974273],"domain_scores_gemma":[0.9988361,0.0002034706,0.00011358,0.000678884,0.00009635371,0.00007163196],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00000768085,0.0004879555,0.1689797,0.001201408,0.0001255028,0.004053477,0.01931692,0.2495115,0.1688782,0.2136019,0.00005583643,0.1737798],"study_design_scores_gemma":[0.00002643796,0.00001739625,0.0002829259,0.0003891477,0.000005276687,0.0005368585,0.002755229,0.9472306,0.04824324,0.0001730422,0.000139863,0.0002000013],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.512637,0.0008043644,0.4843455,0.0002387598,0.0004187739,0.0001839112,0.000001101736,0.0003892004,0.0009813926],"genre_scores_gemma":[0.9817777,0.000009036089,0.01778167,0.00003353324,0.00005542549,0.00002009109,0.000006511802,0.00001957387,0.0002964408],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.697719,"threshold_uncertainty_score":0.8166111,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03773554912136949,"score_gpt":0.2826640071354186,"score_spread":0.2449284580140491,"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."}}