{"id":"W3116083993","doi":"10.1609/aaai.v35i15.17627","title":"Learning Contextual Representations for Semantic Parsing with Generation-Augmented Pre-Training","year":2021,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Topic Modeling","field":"Computer Science","cited_by":75,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Natural language processing; Utterance; Artificial intelligence; Parsing; Leverage (statistics); Schema (genetic algorithms); SQL; Language model; Information retrieval; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001522316,0.001691091,0.0007848316,0.0008336882,0.0005226561,0.0008366901,0.002103564,0.001276574,0.004466098],"category_scores_gemma":[0.005753723,0.000717053,0.00107611,0.001001851,0.000791762,0.003025438,0.001686048,0.003186954,0.001859354],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00101778,"about_ca_system_score_gemma":0.001749417,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00649394,"about_ca_topic_score_gemma":0.01714286,"domain_scores_codex":[0.998969,0.0004262923,0.00004631012,0.0003600055,0.0001020852,0.00009639945],"domain_scores_gemma":[0.9971615,0.001787459,0.00009862869,0.0006096778,0.0002732773,0.00006944127],"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":[0.0005200224,0.0005345633,0.005356467,0.0004880729,0.0001877165,0.0004551202,0.0007177239,0.378659,0.01699608,0.01095685,0.0311188,0.5540097],"study_design_scores_gemma":[0.00003115591,0.00008194653,0.000540661,0.00002339437,0.00003800114,0.00006157292,0.00009011119,0.9764665,0.007665981,0.01124039,0.003743034,0.00001718138],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.07405981,0.0009637151,0.8864401,0.0007312592,0.0001501355,0.0002110064,0.002295389,0.03197186,0.003176593],"genre_scores_gemma":[0.5316002,0.0004263009,0.4472195,0.0007646697,0.00009455292,0.0005598839,0.01504978,0.001394612,0.002890489],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.00649394,"threshold_uncertainty_score":0.01494056,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1511185580312519,"score_gpt":0.331868255043637,"score_spread":0.1807496970123851,"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."}}