In this paper, we present a unified knowledge based approach for sense disambiguation and semantic role labeling. Our approach performs both tasks through a single algorithm that matches candidate semantic interpretations to background knowledge to select the best matching candidate. We evaluate our approach on a corpus of sentences collected from various domains and show how our approach performs well on both sense disambiguation and semantic role labeling.

PDF

In Proceedings of the Twenty-First National Conference on Artificial Intelligence 2006.

@InProceedings{aaai06-unified-approach, title={A Unified Knowledge Based Approach for Sense Disambiguation and Semantic Role Labeling}, author={Peter Yeh and Bruce Porter and Ken Barker}, booktitle={Proceedings of the Twenty-First National Conference on Artificial Intelligence}, url="http://www.cs.utexas.edu/users/ai-lab?aaai06-unified-approach", year={2006} }