A Full Non-Monotonic Transition System for Unrestricted Non-Projective Parsing

Daniel Fernández-González, Carlos Gómez-Rodríguez


Abstract
Restricted non-monotonicity has been shown beneficial for the projective arc-eager dependency parser in previous research, as posterior decisions can repair mistakes made in previous states due to the lack of information. In this paper, we propose a novel, fully non-monotonic transition system based on the non-projective Covington algorithm. As a non-monotonic system requires exploration of erroneous actions during the training process, we develop several non-monotonic variants of the recently defined dynamic oracle for the Covington parser, based on tight approximations of the loss. Experiments on datasets from the CoNLL-X and CoNLL-XI shared tasks show that a non-monotonic dynamic oracle outperforms the monotonic version in the majority of languages.
Anthology ID:
P17-1027
Volume:
Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
Month:
July
Year:
2017
Address:
Vancouver, Canada
Editors:
Regina Barzilay, Min-Yen Kan
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
288–298
Language:
URL:
https://aclanthology.org/P17-1027
DOI:
10.18653/v1/P17-1027
Bibkey:
Cite (ACL):
Daniel Fernández-González and Carlos Gómez-Rodríguez. 2017. A Full Non-Monotonic Transition System for Unrestricted Non-Projective Parsing. In Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 288–298, Vancouver, Canada. Association for Computational Linguistics.
Cite (Informal):
A Full Non-Monotonic Transition System for Unrestricted Non-Projective Parsing (Fernández-González & Gómez-Rodríguez, ACL 2017)
Copy Citation:
PDF:
https://preview.aclanthology.org/nschneid-patch-3/P17-1027.pdf
Video:
 https://preview.aclanthology.org/nschneid-patch-3/P17-1027.mp4