Conditional Bilingual Mutual Information Based Adaptive Training for Neural Machine Translation

TL;DR

This paper introduces a target-context-aware statistical metric called CBMI for adaptive training in neural machine translation, improving translation quality by better weighting target tokens based on context.

Contribution

The paper proposes CBMI, a novel efficient metric that incorporates target context into token weighting, enhancing adaptive training for neural machine translation.

Findings

Significant improvements over baseline models on WMT datasets.

Efficient computation of CBMI without large storage overhead.

Outperforms existing adaptive training methods.

Abstract

Token-level adaptive training approaches can alleviate the token imbalance problem and thus improve neural machine translation, through re-weighting the losses of different target tokens based on specific statistical metrics (e.g., token frequency or mutual information). Given that standard translation models make predictions on the condition of previous target contexts, we argue that the above statistical metrics ignore target context information and may assign inappropriate weights to target tokens. While one possible solution is to directly take target contexts into these statistical metrics, the target-context-aware statistical computing is extremely expensive, and the corresponding storage overhead is unrealistic. To solve the above issues, we propose a target-context-aware metric, named conditional bilingual mutual information (CBMI), which makes it feasible to supplement target context information for statistical metrics. Particularly, our CBMI can be formalized as the log quotient of the translation model probability and language model probability by decomposing the conditional joint distribution. Thus CBMI can be efficiently calculated during model training without any pre-specific statistical calculations and large storage overhead. Furthermore, we propose an effective adaptive training approach based on both the token- and sentence-level CBMI. Experimental results on WMT14 English-German and WMT19 Chinese-English tasks show our approach can significantly outperform the Transformer baseline and other related methods.