Improving Low-Resource Machine Translation via Round-Trip Reinforcement Learning

TL;DR

This paper introduces a reinforcement learning method that improves low-resource machine translation by using round-trip translation and reward functions to enhance fluency and semantic accuracy.

Contribution

It proposes a novel self-supervised reinforcement learning approach with round-trip bootstrapping to improve low-resource language translation quality.

Findings

Consistent improvements across multiple low-resource languages.

Enhanced fluency and semantic fidelity in translations.

Method benefits from larger model scales and pretraining.

Abstract

Low-resource machine translation (MT) has gained increasing attention as parallel data from low-resource language communities is collected, but many approaches for improving low-resource MT remain underexplored. We investigate a self-supervised reinforcement learning fine-tuning for translation in low-resource settings using round-trip bootstrapping with the No Language Left Behind (NLLB) family of models. Our approach translates English into a target low-resource language and then back into English, using a combination of chrF++ and BLEU as the reward function on the reconstructed English sentences. Using the NLLB-MD dataset, we evaluate both the 600M and 1.3B parameter NLLB models and observe consistent improvements for the following languages: Central Aymara, Friulian, Wolof, Dyula, Bhojpuri and Russian. Qualitative inspection of translation outputs indicates increased fluency and semantic fidelity. We argue that our method can further benefit from scale, enabling models to increasingly leverage their pretrained knowledge and continue self-improving. Code available at: https://github.com/Copticoder/MT-via-Round-Trip-RL