Evaluating a Focus-Based Approach to Anaphora Resolution
cmp-lg
2007-05-23 v1 Computation and Language
Abstract
We present an approach to anaphora resolution based on a focusing algorithm, and implemented within an existing MUC (Message Understanding Conference) Information Extraction system, allowing quantitative evaluation against a substantial corpus of annotated real-world texts. Extensions to the basic focusing mechanism can be easily tested, resulting in refinements to the mechanism and resolution rules. Results are compared with the results of a simpler heuristic-based approach.
Cite
@article{arxiv.cmp-lg/9807001,
title = {Evaluating a Focus-Based Approach to Anaphora Resolution},
author = {Saliha Azzam and Kevin Humphreys and Robert Gaizauskas},
journal= {arXiv preprint arXiv:cmp-lg/9807001},
year = {2007}
}
Comments
5 pages, uses colacl.sty