{"id":"W4385567069","doi":"10.18653/v1/2022.findings-emnlp.388","title":"Cross-lingual Text-to-SQL Semantic Parsing with Representation Mixup","year":2022,"lang":"en","type":"article","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; Compute Canada","keywords":"Computer science; Parsing; Natural language processing; Artificial intelligence; SQL; Task (project management); Programming language; Information retrieval","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"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":[0.004125655,0.002594722,0.00156434,0.001646357,0.001018249,0.002796327,0.003284003,0.001676309,0.009958453],"category_scores_gemma":[0.0089809,0.001196595,0.001747394,0.001842775,0.00131573,0.008653222,0.0080303,0.003661025,0.006690642],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008904812,"about_ca_system_score_gemma":0.002714566,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003501132,"about_ca_topic_score_gemma":0.004731628,"domain_scores_codex":[0.9964669,0.001113598,0.000332729,0.00120045,0.0005701155,0.0003162675],"domain_scores_gemma":[0.9954482,0.00176811,0.0002905805,0.001576126,0.0007584609,0.0001584396],"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":[0.0006945739,0.0006909196,0.003259438,0.0009137215,0.0003130865,0.001172357,0.001835078,0.03298667,0.06067104,0.02775824,0.03789862,0.8318062],"study_design_scores_gemma":[0.0001357487,0.000396622,0.001455475,0.0001275901,0.0002904276,0.001420086,0.001112547,0.7178237,0.1724404,0.04926703,0.05530054,0.0002298738],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02324307,0.0003682141,0.9018968,0.0004643254,0.0001355905,0.0003087307,0.0008892423,0.0684398,0.004254139],"genre_scores_gemma":[0.254152,0.0003305244,0.7261224,0.0007461127,0.0001049364,0.0003382899,0.006607064,0.005228283,0.006370336],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.009958453,"threshold_uncertainty_score":0.03331435,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0164783422746464,"score_gpt":0.3199254176967373,"score_spread":0.3034470754220909,"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."}}