English

You May Not Need Attention

Computation and Language 2018-11-01 v1

Abstract

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.

Keywords

Cite

@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}
}
R2 v1 2026-06-23T04:59:25.027Z