Straight to the Tree: Constituency Parsing with Neural Syntactic Distance

Yikang Shen, Zhouhan Lin, Athul Paul Jacob, Alessandro Sordoni, Aaron Courville, Yoshua Bengio


Abstract
In this work, we propose a novel constituency parsing scheme. The model first predicts a real-valued scalar, named syntactic distance, for each split position in the sentence. The topology of grammar tree is then determined by the values of syntactic distances. Compared to traditional shift-reduce parsing schemes, our approach is free from the potentially disastrous compounding error. It is also easier to parallelize and much faster. Our model achieves the state-of-the-art single model F1 score of 92.1 on PTB and 86.4 on CTB dataset, which surpasses the previous single model results by a large margin.
Anthology ID:
P18-1108
Volume:
Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
Month:
July
Year:
2018
Address:
Melbourne, Australia
Editors:
Iryna Gurevych, Yusuke Miyao
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
1171–1180
Language:
URL:
https://aclanthology.org/P18-1108
DOI:
10.18653/v1/P18-1108
Bibkey:
Cite (ACL):
Yikang Shen, Zhouhan Lin, Athul Paul Jacob, Alessandro Sordoni, Aaron Courville, and Yoshua Bengio. 2018. Straight to the Tree: Constituency Parsing with Neural Syntactic Distance. In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 1171–1180, Melbourne, Australia. Association for Computational Linguistics.
Cite (Informal):
Straight to the Tree: Constituency Parsing with Neural Syntactic Distance (Shen et al., ACL 2018)
Copy Citation:
PDF:
https://aclanthology.org/P18-1108.pdf
Presentation:
 P18-1108.Presentation.pdf
Video:
 https://aclanthology.org/P18-1108.mp4
Code
 additional community code