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
- 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
- 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)
- PDF:
- https://preview.aclanthology.org/starsem-semeval-split/D17-1172.pdf