In NMT, how far can we get without attention and without separate encoding and decoding? To answer that question, we introduce a recurrent neural translation model that does not use attention and does not have a separate encoder and decoder. Our eager translation model is low-latency, writing target tokens as soon as it reads the first source token, and uses constant memory during decoding. It performs on par with the standard attention-based model of Bahdanau et al. (2014), and better on long sentences.
@article{arxiv.1810.13409,
title = {You May Not Need Attention},
author = {Ofir Press and Noah A. Smith},
journal= {arXiv preprint arXiv:1810.13409},
year = {2018}
}