PTB Graph Parsing with Tree Approximation

Yoshihide Kato, Shigeki Matsubara


Abstract
The Penn Treebank (PTB) represents syntactic structures as graphs due to nonlocal dependencies. This paper proposes a method that approximates PTB graph-structured representations by trees. By our approximation method, we can reduce nonlocal dependency identification and constituency parsing into single tree-based parsing. An experimental result demonstrates that our approximation method with an off-the-shelf tree-based constituency parser significantly outperforms the previous methods in nonlocal dependency identification.
Anthology ID:
P19-1530
Volume:
Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics
Month:
July
Year:
2019
Address:
Florence, Italy
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
5344–5349
Language:
URL:
https://aclanthology.org/P19-1530
DOI:
10.18653/v1/P19-1530
Bibkey:
Cite (ACL):
Yoshihide Kato and Shigeki Matsubara. 2019. PTB Graph Parsing with Tree Approximation. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 5344–5349, Florence, Italy. Association for Computational Linguistics.
Cite (Informal):
PTB Graph Parsing with Tree Approximation (Kato & Matsubara, ACL 2019)
Copy Citation:
PDF:
https://aclanthology.org/P19-1530.pdf
Code
 yosihide/ptb2cf
Data
Penn Treebank