This paper describes a system, WOLFIE (WOrd Learning From Interpreted Examples), that acquires a semantic lexicon from a corpus of sentences paired with representations of their meaning. The lexicon learned consists of words paired with meaning representations. WOLFIE is part of an integrated system that learns to parse novel sentences into semantic representations, such as logical database queries. Experimental results are presented demonstrating WOLFIE's ability to learn useful lexicons for a database interface in four different natural languages. The lexicons learned by WOLFIE are compared to those acquired by a competing system developed by Siskind (1996).

PDF, PS

In Proceedings of the Sixth Workshop on Very Large Corpora, Montreal, Quebec, Canada, August 1998. Also available as TR AI 98-273, Artificial Intelligence Lab, University of Texas at Austin, May 1998.

@InProceedings{thompson:semlex, title={Semantic Lexicon Acquisition for Learning Natural Language Interfaces}, author={Cynthia A. Thompson and Raymond J. Mooney}, booktitle={Proceedings of the Sixth Workshop on Very Large Corpora}, month={August}, address={Montreal, Quebec, Canada}, note={Also available as TR AI 98-273, Artificial Intelligence Lab, University of Texas at Austin, May 1998}, url="http://www.cs.utexas.edu/users/ai-lab?thompson:semlex", year={1998} }