%0 Conference Proceedings %A Kehler, A., Appelt, D. E., Taylor L., Simma, A %T Competitive Self-Trained Pronoun Interpretation %B Proceedings of the Human Language Technology Conference %P 33-36 %D 2004 %X 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. %U http://www.ai.sri.com/pubs/files/1064.pdf
