Evaluating the Impact of a Hierarchical Discourse Representation on Entity Coreference Resolution Performance
Computation and Language
2021-04-22 v1 Artificial Intelligence
Machine Learning
Abstract
Recent work on entity coreference resolution (CR) follows current trends in Deep Learning applied to embeddings and relatively simple task-related features. SOTA models do not make use of hierarchical representations of discourse structure. In this work, we leverage automatically constructed discourse parse trees within a neural approach and demonstrate a significant improvement on two benchmark entity coreference-resolution datasets. We explore how the impact varies depending upon the type of mention.
Keywords
Cite
@article{arxiv.2104.10215,
title = {Evaluating the Impact of a Hierarchical Discourse Representation on Entity Coreference Resolution Performance},
author = {Sopan Khosla and James Fiacco and Carolyn Rose},
journal= {arXiv preprint arXiv:2104.10215},
year = {2021}
}
Comments
Also contains the Appendix. Accepted to NAACL 2021 as a short paper