Showing 1–18 of 18 results
/ Date/ Name
Nov 7, 2018Blockwise Parallel Decoding for Deep Autoregressive ModelsJan 15, 2020Insertion-Deletion TransformerOct 29, 2019An Empirical Study of Generation Order for Machine TranslationApr 20, 2018What's Going On in Neural Constituency Parsers? An AnalysisMay 12, 2020Semantic Scaffolds for Pseudocode-to-Code GenerationFeb 8, 2019Insertion Transformer: Flexible Sequence Generation via Insertion OperationsJul 27, 2017Effective Inference for Generative Neural ParsingMay 10, 2017A Minimal Span-Based Neural Constituency ParserApr 25, 2017Abstract Syntax Networks for Code Generation and Semantic ParsingJul 4, 2017Kernel Feature Selection via Conditional Covariance MinimizationApr 30, 2020Imitation Attacks and Defenses for Black-box Machine Translation SystemsMay 23, 2017The Marginal Value of Adaptive Gradient Methods in Machine LearningNov 8, 2017Stochastic Cubic Regularization for Fast Nonconvex OptimizationApr 11, 2018Adafactor: Adaptive Learning Rates with Sublinear Memory CostOct 20, 2020Towards End-to-End In-Image Neural Machine TranslationMar 25, 2021Dynamic Posted-Price Mechanisms for the Blockchain Transaction Fee MarketJun 4, 2019KERMIT: Generative Insertion-Based Modeling for SequencesJul 10, 2017Improving Neural Parsing by Disentangling Model Combination and Reranking Effects