Energy-Based Reranking: Improving Neural Machine Translation Using Energy-Based Models

TL;DR

This paper introduces an energy-based re-ranking method that leverages energy models trained to favor higher BLEU score samples, significantly improving neural machine translation performance across multiple datasets.

Contribution

It proposes a novel energy-based re-ranking approach that enhances NMT by training energy models to prioritize higher quality translation samples, bridging the gap between training objectives and evaluation metrics.

Findings

Improves BLEU scores by up to 4 points on IWSLT'14 German-English

Achieves +3.0 BLEU on Sinhala-English translation

Enhances WMT'16 English-German translation performance

Abstract

The discrepancy between maximum likelihood estimation (MLE) and task measures such as BLEU score has been studied before for autoregressive neural machine translation (NMT) and resulted in alternative training algorithms (Ranzato et al., 2016; Norouzi et al., 2016; Shen et al., 2016; Wu et al., 2018). However, MLE training remains the de facto approach for autoregressive NMT because of its computational efficiency and stability. Despite this mismatch between the training objective and task measure, we notice that the samples drawn from an MLE-based trained NMT support the desired distribution -- there are samples with much higher BLEU score comparing to the beam decoding output. To benefit from this observation, we train an energy-based model to mimic the behavior of the task measure (i.e., the energy-based model assigns lower energy to samples with higher BLEU score), which is resulted in a re-ranking algorithm based on the samples drawn from NMT: energy-based re-ranking (EBR). We use both marginal energy models (over target sentence) and joint energy models (over both source and target sentences). Our EBR with the joint energy model consistently improves the performance of the Transformer-based NMT: +4 BLEU points on IWSLT'14 German-English, +3.0 BELU points on Sinhala-English, +1.2 BLEU on WMT'16 English-German tasks.