Representation Learning and Dynamic Programming for Arc-Hybrid Parsing

Joseph Le Roux, Antoine Rozenknop, Mathieu Lacroix


Abstract
We present a new method for transition-based parsing where a solution is a pair made of a dependency tree and a derivation graph describing the construction of the former. From this representation we are able to derive an efficient parsing algorithm and design a neural network that learns vertex representations and arc scores. Experimentally, although we only train via local classifiers, our approach improves over previous arc-hybrid systems and reach state-of-the-art parsing accuracy.
Anthology ID:
K19-1023
Volume:
Proceedings of the 23rd Conference on Computational Natural Language Learning (CoNLL)
Month:
November
Year:
2019
Address:
Hong Kong, China
Venue:
CoNLL
SIG:
SIGNLL
Publisher:
Association for Computational Linguistics
Note:
Pages:
238–248
Language:
URL:
https://aclanthology.org/K19-1023
DOI:
10.18653/v1/K19-1023
Bibkey:
Cite (ACL):
Joseph Le Roux, Antoine Rozenknop, and Mathieu Lacroix. 2019. Representation Learning and Dynamic Programming for Arc-Hybrid Parsing. In Proceedings of the 23rd Conference on Computational Natural Language Learning (CoNLL), pages 238–248, Hong Kong, China. Association for Computational Linguistics.
Cite (Informal):
Representation Learning and Dynamic Programming for Arc-Hybrid Parsing (Le Roux et al., CoNLL 2019)
Copy Citation:
PDF:
https://preview.aclanthology.org/auto-file-uploads/K19-1023.pdf