Improving Neural Text Normalization with Data Augmentation at Character- and Morphological Levels

In this study, we investigated the effectiveness of augmented data for encoderdecoder-based neural normalization models. Attention based encoder-decoder models are greatly effective in generating many natural languages. In general, we have to prepare for a large amount of training data to train an encoderdecoder model. Unlike machine translation, there are few training data for textnormalization tasks. In this paper, we propose two methods for generating augmented data. The experimental results with Japanese dialect normalization indicate that our methods are effective for an encoder-decoder model and achieve higher BLEU score than that of baselines. We also investigated the oracle performance and revealed that there is sufficient room for improving an encoder-decoder model.