Generalized chart constraints for efficient PCFG and TAG parsing

Stefan Grünewald, Sophie Henning, Alexander Koller


Abstract
Chart constraints, which specify at which string positions a constituent may begin or end, have been shown to speed up chart parsers for PCFGs. We generalize chart constraints to more expressive grammar formalisms and describe a neural tagger which predicts chart constraints at very high precision. Our constraints accelerate both PCFG and TAG parsing, and combine effectively with other pruning techniques (coarse-to-fine and supertagging) for an overall speedup of two orders of magnitude, while improving accuracy.
Anthology ID:
P18-2099
Volume:
Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)
Month:
July
Year:
2018
Address:
Melbourne, Australia
Editors:
Iryna Gurevych, Yusuke Miyao
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
626–631
Language:
URL:
https://aclanthology.org/P18-2099
DOI:
10.18653/v1/P18-2099
Bibkey:
Cite (ACL):
Stefan Grünewald, Sophie Henning, and Alexander Koller. 2018. Generalized chart constraints for efficient PCFG and TAG parsing. In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pages 626–631, Melbourne, Australia. Association for Computational Linguistics.
Cite (Informal):
Generalized chart constraints for efficient PCFG and TAG parsing (Grünewald et al., ACL 2018)
Copy Citation:
PDF:
https://preview.aclanthology.org/naacl24-info/P18-2099.pdf
Note:
 P18-2099.Notes.pdf