{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003825992,0.000163637,0.00021808,0.00007344825,0.0003964456,0.0003725564,0.0007166122,0.00005505682,0.00001885838],"category_scores_gemma":[0.0007092346,0.0001304781,0.00008258459,0.0004498283,0.0001149532,0.0004165696,0.0001814722,0.0002269328,0.000005471295],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003571093,"about_ca_system_score_gemma":0.0002218145,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002577237,"about_ca_topic_score_gemma":0.00003631218,"domain_scores_codex":[0.9982929,0.0000255322,0.0004541541,0.0005498551,0.0003765163,0.0003010138],"domain_scores_gemma":[0.9981703,0.0001545204,0.0003027442,0.0002595226,0.001048811,0.0000641117],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00003624072,0.00008161885,0.0004285835,0.00004262788,0.00003743608,0.000001111812,0.008680462,0.006309694,0.1517067,0.7539288,0.00004612219,0.07870065],"study_design_scores_gemma":[0.00004782391,0.0001290582,0.00005495487,0.000198162,0.0000160338,0.00001089826,0.002755524,0.598484,0.3818281,0.01628483,0.00004601164,0.000144571],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.300071,0.00001864015,0.6943529,0.002961408,0.0002510254,0.000382507,0.000001819012,0.00008400615,0.001876642],"genre_scores_gemma":[0.9688143,0.000009130716,0.03032062,0.0001455535,0.0001025219,0.00005308087,0.000002088922,0.00001202195,0.0005407175],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.737644,"threshold_uncertainty_score":0.5320745,"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."}}