Publication Details

Competitive Self-Trained Pronoun Interpretation

by Kehler, A., Appelt, D. E., Taylor L., Simma, A

in Proceedings of the Human Language Technology Conference pp. 33-36,

Organization: North American Chapter of the Association for Computational Linguistics
2004.

We describe a system for pronoun interpretation that is self-trained from raw data, that is, using no annotated training data. The result outperforms a Hobbsian baseline algorithm and is only marginally inferior to an essentially identical, state-of-the-art supervised model trained from a substantial manually-annotated coreference corpus.