Effective Online Reordering with Arc-Eager Transitions

Ryosuke Kohita, Hiroshi Noji, Yuji Matsumoto


Abstract
We present a new transition system with word reordering for unrestricted non-projective dependency parsing. Our system is based on decomposed arc-eager rather than arc-standard, which allows more flexible ambiguity resolution between a local projective and non-local crossing attachment. In our experiment on Universal Dependencies 2.0, we find our parser outperforms the ordinary swap-based parser particularly on languages with a large amount of non-projectivity.
Anthology ID:
W17-6313
Volume:
Proceedings of the 15th International Conference on Parsing Technologies
Month:
September
Year:
2017
Address:
Pisa, Italy
Venues:
IWPT | WS
SIG:
SIGPARSE
Publisher:
Association for Computational Linguistics
Note:
Pages:
88–98
Language:
URL:
https://aclanthology.org/W17-6313
DOI:
Bibkey:
Cite (ACL):
Ryosuke Kohita, Hiroshi Noji, and Yuji Matsumoto. 2017. Effective Online Reordering with Arc-Eager Transitions. In Proceedings of the 15th International Conference on Parsing Technologies, pages 88–98, Pisa, Italy. Association for Computational Linguistics.
Cite (Informal):
Effective Online Reordering with Arc-Eager Transitions (Kohita et al., 2017)
Copy Citation:
PDF:
https://aclanthology.org/W17-6313.pdf