Advances in Using Grammars with Latent Annotations for Discontinuous Parsing

Kilian Gebhardt


Abstract
We present new experiments that transfer techniques from Probabilistic Context-free Grammars with Latent Annotations (PCFG-LA) to two grammar formalisms for discontinuous parsing: linear context-free rewriting systems and hybrid grammars. In particular, Dirichlet priors during EM training, ensemble models, and a new nonterminal scheme for hybrid grammars are evaluated. We find that our grammars are more accurate than previous approaches based on discontinuous grammar formalisms and early instances of the discriminative models but inferior to recent discriminative parsers.
Anthology ID:
2020.iwpt-1.9
Volume:
Proceedings of the 16th International Conference on Parsing Technologies and the IWPT 2020 Shared Task on Parsing into Enhanced Universal Dependencies
Month:
July
Year:
2020
Address:
Online
Editors:
Gosse Bouma, Yuji Matsumoto, Stephan Oepen, Kenji Sagae, Djamé Seddah, Weiwei Sun, Anders Søgaard, Reut Tsarfaty, Dan Zeman
Venue:
IWPT
SIG:
SIGPARSE
Publisher:
Association for Computational Linguistics
Note:
Pages:
91–97
Language:
URL:
https://aclanthology.org/2020.iwpt-1.9
DOI:
10.18653/v1/2020.iwpt-1.9
Bibkey:
Cite (ACL):
Kilian Gebhardt. 2020. Advances in Using Grammars with Latent Annotations for Discontinuous Parsing. In Proceedings of the 16th International Conference on Parsing Technologies and the IWPT 2020 Shared Task on Parsing into Enhanced Universal Dependencies, pages 91–97, Online. Association for Computational Linguistics.
Cite (Informal):
Advances in Using Grammars with Latent Annotations for Discontinuous Parsing (Gebhardt, IWPT 2020)
Copy Citation:
PDF:
https://aclanthology.org/2020.iwpt-1.9.pdf
Video:
 http://slideslive.com/38929676