Multi-Layer Pseudo-Siamese Biaffine Model for Dependency Parsing

Ziyao Xu, Houfeng Wang, Bingdong Wang


Abstract
Biaffine method is a strong and efficient method for graph-based dependency parsing. However, previous work only used the biaffine method at the end of the dependency parser as a scorer, and its application in multi-layer form is ignored. In this paper, we propose a multi-layer pseudo-Siamese biaffine model for neural dependency parsing. In this model, we modify the biaffine method so that it can be utilized in multi-layer form, and use pseudo-Siamese biaffine module to construct arc weight matrix for final prediction. In our proposed multi-layer architecture, the biaffine method plays important roles in both scorer and attention mechanism at the same time in each layer. We evaluate our model on PTB, CTB, and UD. The model achieves state-of-the-art results on these datasets. Further experiments show the benefits of introducing multi-layer form and pseudo-Siamese module into the biaffine method with low efficiency loss.
Anthology ID:
2022.coling-1.486
Volume:
Proceedings of the 29th International Conference on Computational Linguistics
Month:
October
Year:
2022
Address:
Gyeongju, Republic of Korea
Venue:
COLING
SIG:
Publisher:
International Committee on Computational Linguistics
Note:
Pages:
5476–5487
Language:
URL:
https://aclanthology.org/2022.coling-1.486
DOI:
Bibkey:
Cite (ACL):
Ziyao Xu, Houfeng Wang, and Bingdong Wang. 2022. Multi-Layer Pseudo-Siamese Biaffine Model for Dependency Parsing. In Proceedings of the 29th International Conference on Computational Linguistics, pages 5476–5487, Gyeongju, Republic of Korea. International Committee on Computational Linguistics.
Cite (Informal):
Multi-Layer Pseudo-Siamese Biaffine Model for Dependency Parsing (Xu et al., COLING 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.coling-1.486.pdf
Code
 xzy-xzy/mlpsb-parser
Data
Penn Treebank