End-to-End Negation Resolution as Graph Parsing

Robin Kurtz, Stephan Oepen, Marco Kuhlmann


Abstract
We present a neural end-to-end architecture for negation resolution based on a formulation of the task as a graph parsing problem. Our approach allows for the straightforward inclusion of many types of graph-structured features without the need for representation-specific heuristics. In our experiments, we specifically gauge the usefulness of syntactic information for negation resolution. Despite the conceptual simplicity of our architecture, we achieve state-of-the-art results on the Conan Doyle benchmark dataset, including a new top result for our best model.
Anthology ID:
2020.iwpt-1.3
Volume:
Proceedings of the 16th International Conference on Parsing Technologies and the IWPT 2020 Shared Task on Parsing into Enhanced Universal Dependencies
Month:
July
Year:
2020
Address:
Online
Venues:
ACL | IWPT | WS
SIG:
SIGPARSE
Publisher:
Association for Computational Linguistics
Note:
Pages:
14–24
Language:
URL:
https://www.aclweb.org/anthology/2020.iwpt-1.3
DOI:
10.18653/v1/2020.iwpt-1.3
Bib Export formats:
BibTeX MODS XML EndNote
PDF:
http://aclanthology.lst.uni-saarland.de/2020.iwpt-1.3.pdf
Video:
 http://slideslive.com/38929670