Multi-layer Biaffine Model for Neural Dependency Parsing

Anonymous

Abstract: The biaffine model is a strong and efficient model for graph-based dependency parsing. However, previous work only used the biaffine method in single-layer form. In this paper, we propose a multi-layer biaffine model for neural dependency parsing. In this model, we modify the biaffine method so that it can be utilized in multi-layer form. We evaluate our model on PTB and CTB and show our model achieves state-of-the-art results on both datasets. Further experiments show the benefits of introducing multi-layer form into the biaffine method with low efficiency loss.