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

by   Yidan Zhang, et al.

Beam search is the most widely used decoding method for neural machine translation (NMT). In practice, the top-1 candidate with the highest log-probability among the n candidates is selected as the preferred one. However, this top-1 candidate may not be the best overall translation among the n-best list. Recently, Minimum Bayes Risk (MBR) decoding has been proposed to improve the quality for NMT, which seeks for a consensus translation that is closest on average to other candidates from the n-best list. We argue that MBR still suffers from the following problems: The utility function only considers the lexical-level similarity between candidates; The expected utility considers the entire n-best list which is time-consuming and inadequate candidates in the tail list may hurt the performance; Only the relationship between candidates is considered. To solve these issues, we design a regularized MBR reranking framework (RMBR), which considers semantic-based similarity and computes the expected utility for each candidate by truncating the list. We expect the proposed framework to further consider the translation quality and model uncertainty of each candidate. Thus the proposed quality regularizer and uncertainty regularizer are incorporated into the framework. Extensive experiments on multiple translation tasks demonstrate the effectiveness of our method.


page 1

page 2

page 3

page 4


Quality-Aware Decoding for Neural Machine Translation

Despite the progress in machine translation quality estimation and evalu...

Sampling-Based Minimum Bayes Risk Decoding for Neural Machine Translation

In neural machine translation (NMT), we search for the mode of the model...

Epsilon Sampling Rocks: Investigating Sampling Strategies for Minimum Bayes Risk Decoding for Machine Translation

Recent advances in machine translation (MT) have shown that Minimum Baye...

Neural Machine Translation by Minimising the Bayes-risk with Respect to Syntactic Translation Lattices

We present a novel scheme to combine neural machine translation (NMT) wi...

Beam Search Strategies for Neural Machine Translation

The basic concept in Neural Machine Translation (NMT) is to train a larg...

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...

ConRPG: Paraphrase Generation using Contexts as Regularizer

A long-standing issue with paraphrase generation is how to obtain reliab...

Please sign up or login with your details

Forgot password? Click here to reset