Deterministic Non-Autoregressive Neural Sequence Modeling by Iterative Refinement

We propose a conditional non-autoregressive neural sequence model based on iterative refinement. The proposed model is designed based on the principles of latent variable models and denoising autoencoders, and is generally applicable to any sequence generation task... (read more)

PDF Abstract EMNLP 2018 PDF EMNLP 2018 Abstract
TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT BENCHMARK
Machine Translation IWSLT2015 English-German Denoising autoencoders (non-autoregressive) BLEU score 27.01 # 4
Machine Translation IWSLT2015 German-English Denoising autoencoders (non-autoregressive) BLEU score 32.43 # 6
Machine Translation WMT2014 English-German Denoising autoencoders (non-autoregressive) BLEU score 21.54 # 36
Machine Translation WMT2014 German-English Denoising autoencoders (non-autoregressive) BLEU score 25.43 # 7
Machine Translation WMT2016 English-Romanian Denoising autoencoders (non-autoregressive) BLEU score 29.66 # 10
Machine Translation WMT2016 Romanian-English Denoising autoencoders (non-autoregressive) BLEU score 30.30 # 11

Methods used in the Paper


METHOD TYPE
🤖 No Methods Found Help the community by adding them if they're not listed; e.g. Deep Residual Learning for Image Recognition uses ResNet