{"id":"W4388477597","doi":"10.18280/ria.370502","title":"Evaluating the Impact of Sentence Tokenization on Indonesian Automated Essay Scoring Using Pretrained Sentence Embeddings","year":2023,"lang":"en","type":"article","venue":"Revue d intelligence artificielle","topic":"Edcuational Technology Systems","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Direktorat Riset and Pengembangan, Universitas Indonesia; Universitas Indonesia","keywords":"Indonesian; Sentence; Natural language processing; Computer science; Lexical analysis; Artificial intelligence; Linguistics; Speech recognition","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":[0.001892232,0.0002118649,0.000254294,0.0003763663,0.0003337626,0.0001119979,0.001219801,0.0001134686,0.00001283137],"category_scores_gemma":[0.0008797499,0.0001652624,0.0001371743,0.003327168,0.0001555352,0.0004061188,0.0002809901,0.0002349518,0.0001489719],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002171286,"about_ca_system_score_gemma":0.0001970803,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001436074,"about_ca_topic_score_gemma":0.000002681695,"domain_scores_codex":[0.9976263,0.0002119412,0.0006720939,0.0005457033,0.000510118,0.0004338508],"domain_scores_gemma":[0.9976231,0.0006118005,0.0004151067,0.0009191777,0.0003693741,0.00006144847],"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":[0.00001137743,0.00004979451,0.003681058,0.00003671285,0.00003039228,0.000008093636,0.003016373,0.8733195,0.1012732,0.009675967,0.00003878361,0.008858802],"study_design_scores_gemma":[0.00003641002,0.0002368562,0.001305611,0.0003414128,0.000006102472,0.00004132602,0.0006113558,0.9357412,0.05992671,0.001599248,0.000001291567,0.0001524782],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6927047,0.00002182797,0.3053414,0.0003777547,0.000287851,0.0003735724,0.000003079936,0.0007339349,0.0001559061],"genre_scores_gemma":[0.995293,0.000008076115,0.004447093,0.00002336558,0.0000504193,0.00002719655,0.000005288849,0.00001923123,0.0001263106],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3025883,"threshold_uncertainty_score":0.6739207,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1194468513359032,"score_gpt":0.3940551344407296,"score_spread":0.2746082831048264,"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."}}