Second-Order Unsupervised Neural Dependency Parsing

Songlin Yang, Yong Jiang, Wenjuan Han, Kewei Tu


Abstract
Most of the unsupervised dependency parsers are based on first-order probabilistic generative models that only consider local parent-child information. Inspired by second-order supervised dependency parsing, we proposed a second-order extension of unsupervised neural dependency models that incorporate grandparent-child or sibling information. We also propose a novel design of the neural parameterization and optimization methods of the dependency models. In second-order models, the number of grammar rules grows cubically with the increase of vocabulary size, making it difficult to train lexicalized models that may contain thousands of words. To circumvent this problem while still benefiting from both second-order parsing and lexicalization, we use the agreement-based learning framework to jointly train a second-order unlexicalized model and a first-order lexicalized model. Experiments on multiple datasets show the effectiveness of our second-order models compared with recent state-of-the-art methods. Our joint model achieves a 10% improvement over the previous state-of-the-art parser on the full WSJ test set.
Anthology ID:
2020.coling-main.347
Volume:
Proceedings of the 28th International Conference on Computational Linguistics
Month:
December
Year:
2020
Address:
Barcelona, Spain (Online)
Editors:
Donia Scott, Nuria Bel, Chengqing Zong
Venue:
COLING
SIG:
Publisher:
International Committee on Computational Linguistics
Note:
Pages:
3911–3924
Language:
URL:
https://aclanthology.org/2020.coling-main.347
DOI:
10.18653/v1/2020.coling-main.347
Bibkey:
Cite (ACL):
Songlin Yang, Yong Jiang, Wenjuan Han, and Kewei Tu. 2020. Second-Order Unsupervised Neural Dependency Parsing. In Proceedings of the 28th International Conference on Computational Linguistics, pages 3911–3924, Barcelona, Spain (Online). International Committee on Computational Linguistics.
Cite (Informal):
Second-Order Unsupervised Neural Dependency Parsing (Yang et al., COLING 2020)
Copy Citation:
PDF:
https://aclanthology.org/2020.coling-main.347.pdf
Code
 sustcsonglin/second-order-neural-dmv
Data
Universal Dependencies