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
- Editors:
- Ellen Riloff, David Chiang, Julia Hockenmaier, Jun’ichi Tsujii
- 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
- 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)
- PDF:
- https://preview.aclanthology.org/ingest-acl-2023-videos/D18-1159.pdf
- Code
- tzshi/valency-parser-emnlp18
- Data
- Penn Treebank