This paper investigates the development and evaluation of machine translation models from Cantonese to English (and backward), where we propose a novel approach to tackle low-resource language translations. Despite recent improvements in Neural Machine Translation (NMT) models with Transformer-based architectures, Cantonese, a language with over 80 million native speakers, has below-par State-of-the-art commercial translation models due to a lack of resources. The main objectives of the study are to develop a model that can effectively translate Cantonese to English and evaluate it against state-of-the-art commercial models. To achieve this, a new parallel corpus has been created by combining different available corpora online with preprocessing and cleaning. In addition, a monolingual Cantonese dataset has been created through web scraping to aid the synthetic parallel corpus generation. Following the data collection process, several approaches, including fine-tuning models, back-translation , and model switch , have been used. The translation quality of models has been evaluated with multiple quality metrics, including lexicon-based metrics (SacreBLEU and hLEPOR) and embedding-space metrics (COMET and BERTscore). Based on the automatic metrics, the best model is selected and compared against the 2 best commercial translators using a new human evaluation framework HOPES . The best model proposed in this investigation (NLLB-mBART) with model switch mechanisms has reached comparable and even better automatic evaluation scores against State-of-the-art commercial models (Bing and Baidu Translators), with a SacreBLEU score of 16.8 on our test set. Furthermore, an open-source web application has been developed to allow users to translate between Cantonese and English, with the different trained models available for effective comparisons between models from this investigation and users. CantonMT is available at https://github.com/kenrickkung/CantoneseTranslation
Read full abstract