{"id":"W7117712979","doi":"10.18280/isi.301117","title":"Transformer-Based Semantic Search Engine with Morphophonemic Stemming for Low-Resource Sundanese Language","year":2025,"lang":"","type":"article","venue":"Ingénierie des systèmes d information","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"","funders":"","keywords":"Natural language; Search engine indexing; Semantics (computer science); Morphophonology","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":[0.0005191393,0.0008027335,0.001290034,0.003870148,0.001022677,0.00154812,0.001030454,0.0007425807,0.01147449],"category_scores_gemma":[0.001619213,0.0003298667,0.0009906556,0.002926434,0.0003214154,0.003199001,0.001946075,0.0006972824,0.006393759],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005143662,"about_ca_system_score_gemma":0.002179444,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00367673,"about_ca_topic_score_gemma":0.008289235,"domain_scores_codex":[0.9993798,0.00009361605,0.0001200584,0.0001538223,0.0001714396,0.00008126254],"domain_scores_gemma":[0.9993172,0.0001676829,0.00003323246,0.0001166656,0.0003234108,0.00004185113],"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":[0.0009377132,0.000417429,0.001940764,0.001474075,0.0002453368,0.000989627,0.0005512292,0.00346197,0.1059685,0.02970298,0.05041909,0.8038913],"study_design_scores_gemma":[0.0005258899,0.0005589459,0.003323701,0.0002029878,0.0007956658,0.003462519,0.001804456,0.528784,0.2345644,0.09484889,0.1308157,0.0003127918],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07497739,0.002115908,0.8215229,0.0005962285,0.0003798512,0.0004925628,0.01023095,0.07577727,0.0139069],"genre_scores_gemma":[0.3303469,0.0008628765,0.627987,0.0003687678,0.0001030389,0.0001879233,0.02776879,0.003001695,0.009372959],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01147449,"threshold_uncertainty_score":0.03838599,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.008117626699749214,"score_gpt":0.2493247019844946,"score_spread":0.2412070752847454,"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."}}