An analysis of the improvement in Japanese dependency analysis using BERT

Abstract

In this paper, we investigate how the accuracy of Japanese dependency analysis is improved by using BERT.We compare two neural models based on BERT and those based only on traditional features.In our experiments, both of the BERT-based models outperformed the accuracy of the models based only on traditional features.We analyze the difference, in terms of the POS combination and the distance between the bunsetsu pairs, to find the main factor of the improvement.