{"id":"W4388441196","doi":"10.18280/isi.280522","title":"Improving Spell Checker Performance for Bahasa Indonesia Using Text Preprocessing Techniques with Deep Learning Models","year":2023,"lang":"en","type":"article","venue":"Ingénierie des systèmes d information","topic":"Edcuational Technology Systems","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Spell; Computer science; Preprocessor; Natural language processing; Artificial intelligence; Deep learning; Data pre-processing; Machine learning; Sociology","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":[0.001274347,0.001315984,0.000942876,0.001539083,0.0005067209,0.001475143,0.00114306,0.0006044207,0.003098698],"category_scores_gemma":[0.008164798,0.0002424068,0.0006750231,0.001435901,0.0003540426,0.001409272,0.0009874207,0.0008310074,0.004592312],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006587002,"about_ca_system_score_gemma":0.00182849,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01257293,"about_ca_topic_score_gemma":0.01794994,"domain_scores_codex":[0.998354,0.0003074894,0.0003231219,0.0004771154,0.0004219241,0.0001164325],"domain_scores_gemma":[0.9949387,0.001732381,0.0007140799,0.001133238,0.001255542,0.0002259416],"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":[0.001277062,0.0004042057,0.02384547,0.0009590319,0.0001812747,0.001387141,0.0004767733,0.01487552,0.05102612,0.0006074522,0.02540916,0.8795509],"study_design_scores_gemma":[0.0003214631,0.001855523,0.110553,0.0005497369,0.0005354773,0.003066236,0.002635739,0.4741518,0.322915,0.004030614,0.07894719,0.0004382345],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7798452,0.005004254,0.1168033,0.001401002,0.001247672,0.0004399279,0.01494784,0.06067698,0.01963369],"genre_scores_gemma":[0.8475859,0.0008118174,0.1186166,0.0003066769,0.00008739049,0.0001271137,0.02233029,0.0008119447,0.00932223],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01257293,"threshold_uncertainty_score":0.0249995,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02938337364325938,"score_gpt":0.2453731933986199,"score_spread":0.2159898197553605,"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."}}