{"id":"W4385572691","doi":"10.18653/v1/2022.emnlp-main.68","title":"ELMER: A Non-Autoregressive Pre-trained Language Model for Efficient and Effective Text Generation","year":2022,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"Renmin University of China","keywords":"Security token; Computer science; Autoregressive model; Inference; Layer (electronics); Language model; Dependency (UML); Speedup; Artificial intelligence; Permutation (music); Text generation; Token passing; Natural language processing; Speech recognition; Parallel computing; Computer network; Statistics; Mathematics","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":[0.0002402585,0.00009048161,0.0001004726,0.00006202549,0.0002359871,0.00006456928,0.0002413398,0.00002083651,0.000007850923],"category_scores_gemma":[0.0000224609,0.00007971717,0.00003664915,0.00007679666,0.00001202817,0.0000891298,0.0002797806,0.00007103443,9.033525e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006276843,"about_ca_system_score_gemma":0.00004366279,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002735118,"about_ca_topic_score_gemma":0.000009070566,"domain_scores_codex":[0.9991397,0.00003847733,0.000113684,0.0003648436,0.0001760602,0.000167221],"domain_scores_gemma":[0.9995464,0.00006485431,0.00004731795,0.0002620168,0.00003462642,0.00004479984],"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":[0.00001347199,0.00005861336,0.00002420969,0.00001620156,0.0000148361,0.000003774131,0.01737663,0.8856148,0.01826453,0.01629977,0.0004376076,0.06187552],"study_design_scores_gemma":[0.0004610131,0.00008380457,0.00009594671,0.000002500872,0.000004590085,0.000005751981,0.00009638952,0.9965819,0.002264577,0.0002611243,0.00003836977,0.0001040363],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2825783,0.00005889497,0.716244,0.0001845373,0.0001065855,0.0005463412,0.000005757693,0.00006451434,0.0002110344],"genre_scores_gemma":[0.9188111,4.436783e-7,0.07945816,0.000278768,0.00005678036,0.0004347773,0.00000504683,0.000006785228,0.0009480914],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6367859,"threshold_uncertainty_score":0.3250772,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01138970139680135,"score_gpt":0.2587601816389067,"score_spread":0.2473704802421054,"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."}}