{"id":"W4381739142","doi":"10.1007/s41870-023-01342-3","title":"A multilingual translator to SQL with database schema pruning to improve self-attention","year":2023,"lang":"en","type":"article","venue":"International Journal of Information Technology","topic":"Topic Modeling","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"Fundação de Amparo à Pesquisa do Estado de São Paulo","keywords":"Computer science; Transformer; SQL; Schema (genetic algorithms); Database schema; Artificial intelligence; Natural language processing; Relational database; Information retrieval; Database; Programming language; Database design","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004105346,0.0000914889,0.0001193965,0.001687252,0.00004423479,0.0001219091,0.001117422,0.00006732439,0.000004210811],"category_scores_gemma":[0.0001965655,0.00007928875,0.00003856467,0.0007364953,0.00001136371,0.001781251,0.0002161551,0.0002046578,0.0001271292],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001007156,"about_ca_system_score_gemma":0.0001311941,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003946573,"about_ca_topic_score_gemma":0.000003349224,"domain_scores_codex":[0.9986678,0.000009746367,0.0005278597,0.0001097858,0.0005169836,0.0001678105],"domain_scores_gemma":[0.9985958,0.00002816689,0.0002808323,0.0002183331,0.00079316,0.00008372578],"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":[0.000133586,0.00008597284,0.001732593,0.00003719923,0.0002508938,0.0001229493,0.006914164,0.01213392,0.04160105,0.04808296,0.0006805727,0.8882241],"study_design_scores_gemma":[0.008599991,0.002429025,0.005324507,0.00118178,0.00005936493,0.002256943,0.005324053,0.6333041,0.2401664,0.006520679,0.0935011,0.001331984],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3385204,0.000003483716,0.6527961,0.007786284,0.000510527,0.000111676,0.00000800087,0.0001975808,0.00006592546],"genre_scores_gemma":[0.6969246,0.000004523666,0.302401,0.0005534065,0.00007657267,0.00001161798,0.000006080019,0.000004755083,0.0000174734],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8868921,"threshold_uncertainty_score":0.3233302,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.00883787912670021,"score_gpt":0.2724044069227138,"score_spread":0.2635665277960136,"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."}}