Using semantic relations to refine coreference decisions
Proceedings of the conference on Human Language Technology and Empirical Methods in Natural Language Processing (2005)
Available from nlp.cs.nyu.edu
or
Abstract
We present a novel mechanism for im- proving reference resolution by using the output of a relation tagger to rescore coreference hypotheses. Experiments show that this new framework can im- prove performance on two quite different languages - English and Chinese.
Sign up today - FREE
Mendeley saves you time finding and organizing research. Learn more
- All your research in one place
- Add and import papers easily
- Access it anywhere, anytime
Start using Mendeley in seconds!
Readership Statistics
3 Readers on Mendeley
by Discipline
by Academic Status
33% Post Doc
33% Ph.D. Student
33% Assistant Professor
by Country
33% China
33% Germany