{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001000608,0.0002329917,0.0002431427,0.0006464569,0.0005107715,0.0004947657,0.0005749335,0.0001968157,0.000001273165],"category_scores_gemma":[0.0001316881,0.0002159405,0.00005043601,0.001287332,0.0001159505,0.009408093,0.0002024204,0.0002221165,0.00004683751],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003137251,"about_ca_system_score_gemma":0.0001649099,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002956425,"about_ca_topic_score_gemma":0.000003048897,"domain_scores_codex":[0.9982236,0.00003897103,0.0006043696,0.0002885429,0.0003802272,0.0004642685],"domain_scores_gemma":[0.998407,0.00008116808,0.0005818727,0.0003788584,0.0004960361,0.00005504542],"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":[0.00008583203,0.00003246461,0.01625057,0.003094756,0.0000915889,0.000005378592,0.01987559,0.1887223,0.006249842,0.01887992,0.00006452249,0.7466473],"study_design_scores_gemma":[0.0002509773,0.0001162873,0.00103211,0.0003449943,0.000009496327,0.0000771053,0.0006231641,0.981921,0.013254,0.001893696,0.0001888299,0.0002883074],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3171033,0.00003344197,0.6800122,0.00002169583,0.00008003869,0.0005183389,0.000001267304,0.001180904,0.001048867],"genre_scores_gemma":[0.867357,0.000008828117,0.1323285,0.00004326839,0.00005379323,0.0001099804,0.0000278718,0.00002147069,0.00004930198],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7931988,"threshold_uncertainty_score":0.8805798,"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."}}