Efficient Discontinuous Phrase-Structure Parsing via the Generalized Maximum Spanning Arborescence

Caio Corro, Joseph Le Roux, Mathieu Lacroix


Abstract
We present a new method for the joint task of tagging and non-projective dependency parsing. We demonstrate its usefulness with an application to discontinuous phrase-structure parsing where decoding lexicalized spines and syntactic derivations is performed jointly. The main contributions of this paper are (1) a reduction from joint tagging and non-projective dependency parsing to the Generalized Maximum Spanning Arborescence problem, and (2) a novel decoding algorithm for this problem through Lagrangian relaxation. We evaluate this model and obtain state-of-the-art results despite strong independence assumptions.
Anthology ID:
D17-1172
Volume:
Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing
Month:
September
Year:
2017
Address:
Copenhagen, Denmark
Editors:
Martha Palmer, Rebecca Hwa, Sebastian Riedel
Venue:
EMNLP
SIG:
SIGDAT
Publisher:
Association for Computational Linguistics
Note:
Pages:
1644–1654
Language:
URL:
https://aclanthology.org/D17-1172
DOI:
10.18653/v1/D17-1172
Bibkey:
Cite (ACL):
Caio Corro, Joseph Le Roux, and Mathieu Lacroix. 2017. Efficient Discontinuous Phrase-Structure Parsing via the Generalized Maximum Spanning Arborescence. In Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, pages 1644–1654, Copenhagen, Denmark. Association for Computational Linguistics.
Cite (Informal):
Efficient Discontinuous Phrase-Structure Parsing via the Generalized Maximum Spanning Arborescence (Corro et al., EMNLP 2017)
Copy Citation:
PDF:
https://aclanthology.org/D17-1172.pdf