papers AI Learner
The Github is limit! Click to go to the new site.

Deterministic Non-Autoregressive Neural Sequence Modeling by Iterative Refinement

2018-08-27
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.

Abstract (translated by Google)
URL

https://arxiv.org/abs/1802.06901

PDF

https://arxiv.org/pdf/1802.06901


Similar Posts

Comments