Viable Dependency Parsing as Sequence Labeling

Michalina Strzyz, David Vilares, Carlos Gómez-Rodríguez


Abstract
We recast dependency parsing as a sequence labeling problem, exploring several encodings of dependency trees as labels. While dependency parsing by means of sequence labeling had been attempted in existing work, results suggested that the technique was impractical. We show instead that with a conventional BILSTM-based model it is possible to obtain fast and accurate parsers. These parsers are conceptually simple, not needing traditional parsing algorithms or auxiliary structures. However, experiments on the PTB and a sample of UD treebanks show that they provide a good speed-accuracy tradeoff, with results competitive with more complex approaches.
Anthology ID:
N19-1077
Volume:
Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)
Month:
June
Year:
2019
Address:
Minneapolis, Minnesota
Editors:
Jill Burstein, Christy Doran, Thamar Solorio
Venue:
NAACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
717–723
Language:
URL:
https://aclanthology.org/N19-1077
DOI:
10.18653/v1/N19-1077
Bibkey:
Cite (ACL):
Michalina Strzyz, David Vilares, and Carlos Gómez-Rodríguez. 2019. Viable Dependency Parsing as Sequence Labeling. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), pages 717–723, Minneapolis, Minnesota. Association for Computational Linguistics.
Cite (Informal):
Viable Dependency Parsing as Sequence Labeling (Strzyz et al., NAACL 2019)
Copy Citation:
PDF:
https://aclanthology.org/N19-1077.pdf
Code
 mstrise/dep2label
Data
Penn Treebank