Abstract: Text classification approaches have usually required task-specific model architectures and huge labelled datasets. Recently, thanks to the rise of text-based transfer learning techniques, it is possible to pre-train a language model in an unsupervised manner and leverage them to perform effectively on downstream tasks. In this work, we focus on Japanese and show the potential use of transfer learning techniques in text classification. Specifically, we perform binary and multi-class sentiment classification on the Rakuten product review and Yahoo movie review datasets. We show that transfer learning-based approaches perform better than task-specific models trained on 3 times as much data. Furthermore, these approaches perform just as well for language modelling pre-trained on only 1/30 of the data. We release our pre-trained models and code as open source.
Read more on https://aclanthology.org/P19-1458/.