English

Language Models not just for Pre-training: Fast Online Neural Noisy Channel Modeling

Computation and Language 2020-11-17 v1

Abstract

Pre-training models on vast quantities of unlabeled data has emerged as an effective approach to improving accuracy on many NLP tasks. On the other hand, traditional machine translation has a long history of leveraging unlabeled data through noisy channel modeling. The same idea has recently been shown to achieve strong improvements for neural machine translation. Unfortunately, na\"{i}ve noisy channel modeling with modern sequence to sequence models is up to an order of magnitude slower than alternatives. We address this issue by introducing efficient approximations to make inference with the noisy channel approach as fast as strong ensembles while increasing accuracy. We also show that the noisy channel approach can outperform strong pre-training results by achieving a new state of the art on WMT Romanian-English translation.

Keywords

Cite

@article{arxiv.2011.07164,
  title  = {Language Models not just for Pre-training: Fast Online Neural Noisy Channel Modeling},
  author = {Shruti Bhosale and Kyra Yee and Sergey Edunov and Michael Auli},
  journal= {arXiv preprint arXiv:2011.07164},
  year   = {2020}
}

Comments

Accepted at WMT 2020