{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00193283,0.001274175,0.001103786,0.001602102,0.000679795,0.002812042,0.002184349,0.0009599257,0.02197479],"category_scores_gemma":[0.008801565,0.00107146,0.001255553,0.001664721,0.0004244948,0.004389043,0.003959315,0.002166231,0.01254288],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005529897,"about_ca_system_score_gemma":0.001537386,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002610413,"about_ca_topic_score_gemma":0.003488395,"domain_scores_codex":[0.9978123,0.0004741361,0.0003428123,0.0006720023,0.000536998,0.000161725],"domain_scores_gemma":[0.992942,0.00232502,0.0002303569,0.002281109,0.002035604,0.0001860357],"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":[0.000989407,0.000596757,0.004393516,0.001239069,0.0003181408,0.0008563914,0.003205136,0.00611403,0.06438523,0.01928038,0.209385,0.6892369],"study_design_scores_gemma":[0.0003477975,0.0002860732,0.002359821,0.0002579234,0.0004891034,0.001158254,0.001536184,0.3987728,0.2132042,0.03435397,0.3470038,0.0002301226],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01666686,0.0003660636,0.7453628,0.000509155,0.0004115859,0.0002177778,0.003539114,0.227525,0.005401596],"genre_scores_gemma":[0.1867311,0.0003839798,0.7222603,0.001265718,0.0002515342,0.0003725495,0.01683947,0.05398795,0.01790741],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.02197479,"threshold_uncertainty_score":0.07351291,"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."}}