An Empirical Investigation of Structured Output Modeling for Graph-based Neural Dependency Parsing

Zhisong Zhang, Xuezhe Ma, Eduard Hovy


Abstract
In this paper, we investigate the aspect of structured output modeling for the state-of-the-art graph-based neural dependency parser (Dozat and Manning, 2017). With evaluations on 14 treebanks, we empirically show that global output-structured models can generally obtain better performance, especially on the metric of sentence-level Complete Match. However, probably because neural models already learn good global views of the inputs, the improvement brought by structured output modeling is modest.
Anthology ID:
P19-1562
Volume:
Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics
Month:
July
Year:
2019
Address:
Florence, Italy
Editors:
Anna Korhonen, David Traum, Lluís Màrquez
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
5592–5598
Language:
URL:
https://aclanthology.org/P19-1562
DOI:
10.18653/v1/P19-1562
Bibkey:
Cite (ACL):
Zhisong Zhang, Xuezhe Ma, and Eduard Hovy. 2019. An Empirical Investigation of Structured Output Modeling for Graph-based Neural Dependency Parsing. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 5592–5598, Florence, Italy. Association for Computational Linguistics.
Cite (Informal):
An Empirical Investigation of Structured Output Modeling for Graph-based Neural Dependency Parsing (Zhang et al., ACL 2019)
Copy Citation:
PDF:
https://preview.aclanthology.org/nschneid-patch-2/P19-1562.pdf
Supplementary:
 P19-1562.Supplementary.pdf
Code
 zzsfornlp/zmsp