Deterministic Non-Autoregressive Neural Sequence Modeling by Iterative Refinement

Jason LeeElman MansimovKyunghyun Cho

   Papers with code   Abstract  PDF

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)

Benchmarked Models

No benchmarked models yet. Click here to submit a model.