{"id":"W4385573402","doi":"10.18653/v1/2022.findings-emnlp.384","title":"XRICL: Cross-lingual Retrieval-Augmented In-Context Learning for Cross-lingual Text-to-SQL Semantic Parsing","year":2022,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":22,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; Compute Canada","keywords":"Computer science; Natural language processing; Artificial intelligence; Parsing; SQL; Information retrieval; Programming language","routes":{"ca_aff":true,"ca_fund":true,"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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001931977,0.0003052946,0.0004006402,0.0003962118,0.001011111,0.0007312924,0.001396644,0.00009328954,0.0001603885],"category_scores_gemma":[0.0007147972,0.0003326733,0.0001717004,0.001056966,0.00005746952,0.0005007635,0.001329515,0.0006660935,0.00004522933],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003779981,"about_ca_system_score_gemma":0.0002682089,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002199795,"about_ca_topic_score_gemma":0.00006698348,"domain_scores_codex":[0.9961864,0.0001453908,0.0008195753,0.001153202,0.0007236056,0.0009717902],"domain_scores_gemma":[0.998273,0.0004254111,0.0001982443,0.0007065521,0.0002006202,0.0001962044],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0005948112,0.0004783662,0.0823202,0.0001843665,0.0000987451,0.0002560182,0.02569047,0.6684267,0.009996794,0.01729821,0.0003934024,0.1942619],"study_design_scores_gemma":[0.002975554,0.0005359167,0.004156821,0.00006944466,0.00001211931,0.00007577376,0.001378292,0.9638138,0.01089922,0.001713023,0.01351834,0.000851694],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6945446,0.0001319546,0.3023915,0.0004514757,0.0009201443,0.0005447881,0.00000289166,0.0003119389,0.0007007138],"genre_scores_gemma":[0.9772909,0.000002037927,0.01642235,0.001101833,0.0001942245,0.00005789195,0.000007698283,0.00004325382,0.004879852],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2953871,"threshold_uncertainty_score":0.9999126,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03103624341915619,"score_gpt":0.3261460489714391,"score_spread":0.2951098055522829,"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."}}