Evaluating Automated and Manual Acquisition of Anaphora Resolution Strategies (1995)
Cached
Download Links
- [acl.ldc.upenn.edu]
- [people.csail.mit.edu]
- [people.csail.mit.edu]
- DBLP
Other Repositories/Bibliography
| Venue: | In Proceedings of the 33rd Annual Meeting of the Association for Computational Linguistics |
| Citations: | 87 - 1 self |
BibTeX
@INPROCEEDINGS{Aone95evaluatingautomated,
author = {Ghinatsu Aone and Scott William Bennett},
title = {Evaluating Automated and Manual Acquisition of Anaphora Resolution Strategies},
booktitle = {In Proceedings of the 33rd Annual Meeting of the Association for Computational Linguistics},
year = {1995},
pages = {122--129}
}
Years of Citing Articles
Bookmark
 |
 |
 |
 |
 |
 |
OpenURL
Abstract
We describe one approach to build an automatically trainable anaphora resolution system. In this approach, we use Japanese newspaper articles tagged with discourse information as training examples for a ms" chine learning algorithm which employs the G4.5 decision tree algorithm by Quinlan (Quinlan, 1993). Then, we evaluate and compare the results of several variants of the machine learning-based approach with those of our existing snaphots resolution system which uses manually-designed knowledge sources. Finally, we compare our algorithms with existing theories of snapbors, in particular, Japanese zero pro- nouns.
