End-to-End Graph-Based TAG Parsing with Neural Networks

Jungo Kasai, Robert Frank, Pauli Xu, William Merrill, Owen Rambow


Abstract
We present a graph-based Tree Adjoining Grammar (TAG) parser that uses BiLSTMs, highway connections, and character-level CNNs. Our best end-to-end parser, which jointly performs supertagging, POS tagging, and parsing, outperforms the previously reported best results by more than 2.2 LAS and UAS points. The graph-based parsing architecture allows for global inference and rich feature representations for TAG parsing, alleviating the fundamental trade-off between transition-based and graph-based parsing systems. We also demonstrate that the proposed parser achieves state-of-the-art performance in the downstream tasks of Parsing Evaluation using Textual Entailments (PETE) and Unbounded Dependency Recovery. This provides further support for the claim that TAG is a viable formalism for problems that require rich structural analysis of sentences.
Anthology ID:
N18-1107
Volume:
Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers)
Month:
June
Year:
2018
Address:
New Orleans, Louisiana
Venue:
NAACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
1181–1194
Language:
URL:
https://www.aclweb.org/anthology/N18-1107
DOI:
10.18653/v1/N18-1107
Bib Export formats:
BibTeX MODS XML EndNote
PDF:
http://aclanthology.lst.uni-saarland.de/N18-1107.pdf
Video:
 http://vimeo.com/276898201