Valency-Augmented Dependency Parsing

Tianze Shi, Lillian Lee


Abstract
We present a complete, automated, and efficient approach for utilizing valency analysis in making dependency parsing decisions. It includes extraction of valency patterns, a probabilistic model for tagging these patterns, and a joint decoding process that explicitly considers the number and types of each token’s syntactic dependents. On 53 treebanks representing 41 languages in the Universal Dependencies data, we find that incorporating valency information yields higher precision and F1 scores on the core arguments (subjects and complements) and functional relations (e.g., auxiliaries) that we employ for valency analysis. Precision on core arguments improves from 80.87 to 85.43. We further show that our approach can be applied to an ostensibly different formalism and dataset, Tree Adjoining Grammar as extracted from the Penn Treebank; there, we outperform the previous state-of-the-art labeled attachment score by 0.7. Finally, we explore the potential of extending valency patterns beyond their traditional domain by confirming their helpfulness in improving PP attachment decisions.
Anthology ID:
D18-1159
Volume:
Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing
Month:
October-November
Year:
2018
Address:
Brussels, Belgium
Venue:
EMNLP
SIG:
SIGDAT
Publisher:
Association for Computational Linguistics
Note:
Pages:
1277–1291
Language:
URL:
https://aclanthology.org/D18-1159
DOI:
10.18653/v1/D18-1159
Bibkey:
Cite (ACL):
Tianze Shi and Lillian Lee. 2018. Valency-Augmented Dependency Parsing. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pages 1277–1291, Brussels, Belgium. Association for Computational Linguistics.
Cite (Informal):
Valency-Augmented Dependency Parsing (Shi & Lee, EMNLP 2018)
Copy Citation:
PDF:
https://aclanthology.org/D18-1159.pdf
Attachment:
 D18-1159.Attachment.zip
Video:
 https://vimeo.com/305214708
Code
 tzshi/valency-parser-emnlp18
Data
Penn Treebank