Understanding the Properties of Minimum Bayes Risk Decoding in Neural Machine Translation

05/18/2021 ∙ by Mathias Müller, et al. ∙ 9

Neural Machine Translation (NMT) currently exhibits biases such as producing translations that are too short and overgenerating frequent words, and shows poor robustness to copy noise in training data or domain shift. Recent work has tied these shortcomings to beam search – the de facto standard inference algorithm in NMT – and Eikema Aziz (2020) propose to use Minimum Bayes Risk (MBR) decoding on unbiased samples instead. In this paper, we empirically investigate the properties of MBR decoding on a number of previously reported biases and failure cases of beam search. We find that MBR still exhibits a length and token frequency bias, owing to the MT metrics used as utility functions, but that MBR also increases robustness against copy noise in the training data and domain shift.

READ FULL TEXT
POST COMMENT

Comments

There are no comments yet.

Authors

page 5

page 6

page 7

page 8

page 13

Code Repositories

This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.