Simpler but More Accurate Semantic Dependency Parsing

Timothy Dozat, Christopher D. Manning


Abstract
While syntactic dependency annotations concentrate on the surface or functional structure of a sentence, semantic dependency annotations aim to capture between-word relationships that are more closely related to the meaning of a sentence, using graph-structured representations. We extend the LSTM-based syntactic parser of Dozat and Manning (2017) to train on and generate these graph structures. The resulting system on its own achieves state-of-the-art performance, beating the previous, substantially more complex state-of-the-art system by 0.6% labeled F1. Adding linguistically richer input representations pushes the margin even higher, allowing us to beat it by 1.9% labeled F1.
Anthology ID:
P18-2077
Volume:
Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)
Month:
July
Year:
2018
Address:
Melbourne, Australia
Editors:
Iryna Gurevych, Yusuke Miyao
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
484–490
Language:
URL:
https://aclanthology.org/P18-2077
DOI:
10.18653/v1/P18-2077
Bibkey:
Cite (ACL):
Timothy Dozat and Christopher D. Manning. 2018. Simpler but More Accurate Semantic Dependency Parsing. In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pages 484–490, Melbourne, Australia. Association for Computational Linguistics.
Cite (Informal):
Simpler but More Accurate Semantic Dependency Parsing (Dozat & Manning, ACL 2018)
Copy Citation:
PDF:
https://aclanthology.org/P18-2077.pdf
Video:
 https://aclanthology.org/P18-2077.mp4
Code
 additional community code
Data
Universal Dependencies