DeepAI AI Chat
Log In Sign Up

Sampling-Based Minimum Bayes Risk Decoding for Neural Machine Translation

by   Bryan Eikema, et al.

In neural machine translation (NMT), we search for the mode of the model distribution to form predictions. The mode as well as other high probability translations found by beam search have been shown to often be inadequate in a number of ways. This prevents practitioners from improving translation quality through better search, as these idiosyncratic translations end up being selected by the decoding algorithm, a problem known as the beam search curse. Recently, a sampling-based approximation to minimum Bayes risk (MBR) decoding has been proposed as an alternative decision rule for NMT that would likely not suffer from the same problems. We analyse this approximation and establish that it has no equivalent to the beam search curse, i.e. better search always leads to better translations. We also design different approximations aimed at decoupling the cost of exploration from the cost of robust estimation of expected utility. This allows for exploration of much larger hypothesis spaces, which we show to be beneficial. We also show that it can be beneficial to make use of strategies like beam search and nucleus sampling to construct hypothesis spaces efficiently. We show on three language pairs (English into and from German, Romanian, and Nepali) that MBR can improve upon beam search with moderate computation.


page 1

page 2

page 3

page 4


Is MAP Decoding All You Need? The Inadequacy of the Mode in Neural Machine Translation

Recent studies have revealed a number of pathologies of neural machine t...

Later-stage Minimum Bayes-Risk Decoding for Neural Machine Translation

For extended periods of time, sequence generation models rely on beam se...

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

Neural Machine Translation (NMT) currently exhibits biases such as produ...

RMBR: A Regularized Minimum Bayes Risk Reranking Framework for Machine Translation

Beam search is the most widely used decoding method for neural machine t...

Learning Efficient Lexically-Constrained Neural Machine Translation with External Memory

Recent years has witnessed dramatic progress of neural machine translati...

Minimum Bayes Risk Decoding with Neural Metrics of Translation Quality

This work applies Minimum Bayes Risk (MBR) decoding to optimize diverse ...

If beam search is the answer, what was the question?

Quite surprisingly, exact maximum a posteriori (MAP) decoding of neural ...