CantonMT: Cantonese to English NMT Platform with Fine-Tuned Models Using Synthetic Back-Translation Data

TL;DR

This paper introduces CantonMT, a platform for Cantonese-to-English neural machine translation that leverages fine-tuned models trained on synthetic back-translation data, improving low-resource language translation.

Contribution

The paper presents a new NMT platform for Cantonese-English translation using synthetic data and fine-tuning, with an open-source toolkit for community contributions.

Findings

Effective back-translation data improves translation quality.

Multiple models like OpusMT, NLLB, mBART enhance performance.

User-friendly interface facilitates research and model addition.

Abstract

Neural Machine Translation (NMT) for low-resource languages is still a challenging task in front of NLP researchers. In this work, we deploy a standard data augmentation methodology by back-translation to a new language translation direction Cantonese-to-English. We present the models we fine-tuned using the limited amount of real data and the synthetic data we generated using back-translation including OpusMT, NLLB, and mBART. We carried out automatic evaluation using a range of different metrics including lexical-based and embedding-based. Furthermore. we create a user-friendly interface for the models we included in this\textsc{ CantonMT} research project and make it available to facilitate Cantonese-to-English MT research. Researchers can add more models into this platform via our open-source\textsc{ CantonMT} toolkit \url{https://github.com/kenrickkung/CantoneseTranslation}.