Extracting a formal representation from text that can be used to reason and answer questions has long been a goal of Artificial Intelligence research. We demonstrate a method for knowledge engineers to construct a semantic interpeter that requires little natural language processing expertise. The resulting semantic interpreter is also able to extend its coverage using semi-supervised learning. We compare the performance of an existing semantic interpretation system to our resulting semantic interpreter. Our semantic interpreter shows considerably superior performance on the two of the three test documents.

PDF

In Proceedings of the Eighth Conference of the Pacific Association for Computational Linguistics 2009.

@inproceedings{pacling09-sinda, title={Constructing a semantic interpreter using distributional analysis}, author={Michael Glass and Ken Barker and Rekha Kumar and Guhan Ravi and Bruce Porter}, booktitle={Proceedings of the Eighth Conference of the Pacific Association for Computational Linguistics}, url="http://www.cs.utexas.edu/users/ai-lab?pacling09-sinda", year={2009} }