Deterministic Non-Autoregressive Neural Sequence Modeling by Iterative Refinement

Jason Lee, Elman Mansimov, Kyunghyun Cho


Abstract
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. We extensively evaluate the proposed model on machine translation (En-De and En-Ro) and image caption generation, and observe that it significantly speeds up decoding while maintaining the generation quality comparable to the autoregressive counterpart.
Anthology ID:
D18-1149
Volume:
Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing
Month:
October-November
Year:
2018
Address:
Brussels, Belgium
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
1173–1182
URL:
https://www.aclweb.org/anthology/D18-1149
DOI:
Bib Export formats:
BibTeX MODS XML EndNote
Attachment:
 D18-1149.Attachment.pdf
Video:
 https://vimeo.com/305207923