Recognizing Referential Links: An Information Extraction Perspective
cmp-lg
2008-02-03 v1 计算与语言
摘要
We present an efficient and robust reference resolution algorithm in an end-to-end state-of-the-art information extraction system, which must work with a considerably impoverished syntactic analysis of the input sentences. Considering this disadvantage, the basic setup to collect, filter, then order by salience does remarkably well with third-person pronouns, but needs more semantic and discourse information to improve the treatments of other expression types.
引用
@article{arxiv.cmp-lg/9707009,
title = {Recognizing Referential Links: An Information Extraction Perspective},
author = {Megumi Kameyama},
journal= {arXiv preprint arXiv:cmp-lg/9707009},
year = {2008}
}
备注
8 pages. a paper in the proceedings of the ACL/EACL'97 workshop on anaphora resolution