English

Guiding Non-Autoregressive Neural Machine Translation Decoding with Reordering Information

Computation and Language 2020-12-17 v2

Abstract

Non-autoregressive neural machine translation (NAT) generates each target word in parallel and has achieved promising inference acceleration. However, existing NAT models still have a big gap in translation quality compared to autoregressive neural machine translation models due to the enormous decoding space. To address this problem, we propose a novel NAT framework named ReorderNAT which explicitly models the reordering information in the decoding procedure. We further introduce deterministic and non-deterministic decoding strategies that utilize reordering information to narrow the decoding search space in our proposed ReorderNAT. Experimental results on various widely-used datasets show that our proposed model achieves better performance compared to existing NAT models, and even achieves comparable translation quality as autoregressive translation models with a significant speedup.

Keywords

Cite

@article{arxiv.1911.02215,
  title  = {Guiding Non-Autoregressive Neural Machine Translation Decoding with Reordering Information},
  author = {Qiu Ran and Yankai Lin and Peng Li and Jie Zhou},
  journal= {arXiv preprint arXiv:1911.02215},
  year   = {2020}
}

Comments

Accepted by AAAI 2021

R2 v1 2026-06-23T12:07:03.085Z