Left-to-Right Dependency Parsing with Pointer Networks

Daniel Fernández-González, Carlos Gómez-Rodríguez


Abstract
We propose a novel transition-based algorithm that straightforwardly parses sentences from left to right by building n attachments, with n being the length of the input sentence. Similarly to the recent stack-pointer parser by Ma et al. (2018), we use the pointer network framework that, given a word, can directly point to a position from the sentence. However, our left-to-right approach is simpler than the original top-down stack-pointer parser (not requiring a stack) and reduces transition sequence length in half, from 2n-1 actions to n. This results in a quadratic non-projective parser that runs twice as fast as the original while achieving the best accuracy to date on the English PTB dataset (96.04% UAS, 94.43% LAS) among fully-supervised single-model dependency parsers, and improves over the former top-down transition system in the majority of languages tested.
Anthology ID:
N19-1076
Volume:
Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)
Month:
June
Year:
2019
Address:
Minneapolis, Minnesota
Editors:
Jill Burstein, Christy Doran, Thamar Solorio
Venue:
NAACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
710–716
Language:
URL:
https://aclanthology.org/N19-1076
DOI:
10.18653/v1/N19-1076
Bibkey:
Cite (ACL):
Daniel Fernández-González and Carlos Gómez-Rodríguez. 2019. Left-to-Right Dependency Parsing with Pointer Networks. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), pages 710–716, Minneapolis, Minnesota. Association for Computational Linguistics.
Cite (Informal):
Left-to-Right Dependency Parsing with Pointer Networks (Fernández-González & Gómez-Rodríguez, NAACL 2019)
Copy Citation:
PDF:
https://aclanthology.org/N19-1076.pdf
Code
 danifg/Left2Right-Pointer-Parser
Data
Penn Treebank