{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002714711,0.001380719,0.0007128619,0.0006932106,0.0002155596,0.0009797786,0.0008036194,0.000690301,0.001772031],"category_scores_gemma":[0.01500656,0.0002289426,0.0004605416,0.0006039209,0.0003220629,0.001472652,0.001017041,0.001154725,0.001800284],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003693038,"about_ca_system_score_gemma":0.000725558,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002600794,"about_ca_topic_score_gemma":0.003572837,"domain_scores_codex":[0.9981228,0.0007268538,0.0002544875,0.0004644807,0.0002851963,0.0001461534],"domain_scores_gemma":[0.9950705,0.002648504,0.0004549049,0.0006489382,0.000975374,0.0002017855],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00201584,0.001295039,0.04449524,0.0009643266,0.0004101306,0.0004637534,0.000443399,0.08400868,0.04182974,0.0007992135,0.01057543,0.8126992],"study_design_scores_gemma":[0.0001228505,0.002472675,0.04292304,0.0001203586,0.000205012,0.0004965614,0.0006143726,0.8882546,0.05742128,0.0008776636,0.00639195,0.00009966514],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.926336,0.00142024,0.06084054,0.0002159192,0.0005393541,0.0002526663,0.002217922,0.005044782,0.003132452],"genre_scores_gemma":[0.9378673,0.0004128651,0.04935504,0.00009266374,0.00007505134,0.0002595946,0.008824266,0.000161713,0.002951437],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.002714711,"threshold_uncertainty_score":0.01435691,"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."}}