Reorder and then Parse, Fast and Accurate Discontinuous Constituency Parsing

Kailai Sun, Zuchao Li, Hai Zhao


Abstract
Discontinuous constituency parsing is still kept developing for its efficiency and accuracy are far behind its continuous counterparts. Motivated by the observation that a discontinuous constituent tree can be simply transformed into a pseudo-continuous one by artificially reordering words in the sentence, we propose a novel reordering method, thereby construct fast and accurate discontinuous constituency parsing systems working in continuous way. Specifically, we model the relative position changes of words as a list of actions. By parsing and performing this actions, the corresponding pseudo-continuous sequence is derived. Discontinuous parse tree can be further inferred via integrating a high-performance pseudo-continuous constituency parser. Our systems are evaluated on three classical discontinuous constituency treebanks, achieving new state-of-the-art on two treebanks and showing a distinct advantage in speed.
Anthology ID:
2022.emnlp-main.723
Volume:
Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing
Month:
December
Year:
2022
Address:
Abu Dhabi, United Arab Emirates
Editors:
Yoav Goldberg, Zornitsa Kozareva, Yue Zhang
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
10575–10588
Language:
URL:
https://aclanthology.org/2022.emnlp-main.723
DOI:
10.18653/v1/2022.emnlp-main.723
Bibkey:
Cite (ACL):
Kailai Sun, Zuchao Li, and Hai Zhao. 2022. Reorder and then Parse, Fast and Accurate Discontinuous Constituency Parsing. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pages 10575–10588, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.
Cite (Informal):
Reorder and then Parse, Fast and Accurate Discontinuous Constituency Parsing (Sun et al., EMNLP 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.emnlp-main.723.pdf