A Conditional Splitting Framework for Efficient Constituency Parsing

Thanh-Tung Nguyen, Xuan-Phi Nguyen, Shafiq Joty, Xiaoli Li


Abstract
We introduce a generic seq2seq parsing framework that casts constituency parsing problems (syntactic and discourse parsing) into a series of conditional splitting decisions. Our parsing model estimates the conditional probability distribution of possible splitting points in a given text span and supports efficient top-down decoding, which is linear in number of nodes. The conditional splitting formulation together with efficient beam search inference facilitate structural consistency without relying on expensive structured inference. Crucially, for discourse analysis we show that in our formulation, discourse segmentation can be framed as a special case of parsing which allows us to perform discourse parsing without requiring segmentation as a pre-requisite. Experiments show that our model achieves good results on the standard syntactic parsing tasks under settings with/without pre-trained representations and rivals state-of-the-art (SoTA) methods that are more computationally expensive than ours. In discourse parsing, our method outperforms SoTA by a good margin.
Anthology ID:
2021.acl-long.450
Volume:
Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)
Month:
August
Year:
2021
Address:
Online
Editors:
Chengqing Zong, Fei Xia, Wenjie Li, Roberto Navigli
Venues:
ACL | IJCNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
5795–5807
Language:
URL:
https://aclanthology.org/2021.acl-long.450
DOI:
10.18653/v1/2021.acl-long.450
Bibkey:
Cite (ACL):
Thanh-Tung Nguyen, Xuan-Phi Nguyen, Shafiq Joty, and Xiaoli Li. 2021. A Conditional Splitting Framework for Efficient Constituency Parsing. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pages 5795–5807, Online. Association for Computational Linguistics.
Cite (Informal):
A Conditional Splitting Framework for Efficient Constituency Parsing (Nguyen et al., ACL-IJCNLP 2021)
Copy Citation:
PDF:
https://preview.aclanthology.org/landing_page/2021.acl-long.450.pdf
Video:
 https://preview.aclanthology.org/landing_page/2021.acl-long.450.mp4
Data
Penn Treebank