{"id":"W4386099755","doi":"10.1007/s00778-023-00809-w","title":"xDBTagger: explainable natural language interface to databases using keyword mappings and schema graph","year":2023,"lang":"en","type":"article","venue":"The VLDB Journal","topic":"Topic Modeling","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Pipeline (software); Schema (genetic algorithms); SQL; Artificial intelligence; Natural language; Natural language processing; Information retrieval; Database; Programming language","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":[0.000747117,0.0001093787,0.0001186814,0.0001929843,0.0003675011,0.0003222619,0.0007108296,0.00001766512,0.00001116405],"category_scores_gemma":[0.00008969635,0.00007542698,0.00003910334,0.0005334483,0.00002996366,0.0005322303,0.0006945565,0.000313745,0.00002992032],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003224304,"about_ca_system_score_gemma":0.0000366327,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006673081,"about_ca_topic_score_gemma":0.000007179886,"domain_scores_codex":[0.9989577,0.00006367297,0.0001819734,0.0002086014,0.0002450366,0.0003430234],"domain_scores_gemma":[0.9993094,0.00008073944,0.0000737453,0.0003796201,0.00004511845,0.0001113621],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001314267,0.0001073739,0.003060452,0.0002112921,0.0003432319,0.001669674,0.1140708,0.0335085,0.4069306,0.02670921,0.03322079,0.3800367],"study_design_scores_gemma":[0.001020422,0.000101312,0.001466011,0.0006860631,0.0000364107,0.003921478,0.009868156,0.931417,0.02650812,0.004766223,0.01939989,0.0008089361],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6806445,0.0009352505,0.3156119,0.002169216,0.0004275265,0.00006224545,0.000001021875,0.00008310599,0.00006516139],"genre_scores_gemma":[0.9465924,0.00005438675,0.05208988,0.0004517366,0.0002319261,0.000001984276,4.708818e-7,0.00001072169,0.0005664963],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8979084,"threshold_uncertainty_score":0.3107579,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04688202870401947,"score_gpt":0.311817887888365,"score_spread":0.2649358591843455,"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."}}