Abstract
Recent machine translation algorithms mainly rely on parallel corpora. However, since the availability of parallel corpora remains limited, only some resource-rich language pairs can benefit from them. In this paper, we constructed a parallel corpus for English-Japanese, where the amount of publicly available parallel corpora is still limited. We constructed a parallel corpus by broadly crawling the web and automatically aligning parallel sentences. Our collected corpus, called JParaCrawl, amassed over 8.7 million sentence pairs. We show how it includes broader domains, and the NMT model trained with it works as a good pre-trained model for fine-tuning specific domains. The pre-training and fine-tuning approaches surpassed or achieved comparable performance to the model training from the initial state and largely reduced the training cost. Additionally, we trained the model with an in-domain dataset and JParaCrawl to show how we achieved the best performance with them. JParaCrawl and the pre-trained models are freely available online for research purposes.
Abstract (translated)
URL
https://arxiv.org/abs/1911.10668
