Semantic parsing is the task of mapping a natural language sentence into a complete, formal meaning representation. Over the past decade, we have developed a number of machine learning methods for inducing semantic parsers by training on a corpus of sentences paired with their meaning representations in a specified formal language. We have demonstrated these methods on the automated construction of natural-language interfaces to databases and robot command languages. This paper reviews our prior work on this topic and discusses directions for future research.

PDF, PS

In Computational Linguistics and Intelligent Text Processing: Proceedings of the 8th International Conference (CICLing 2007), A. Gelbukh (Eds.), pp. 311--324, Mexico City, Mexico, February 2007. Springer: Berlin, Germany. Invited paper.

@inproceedings{mooney:cicling07, title={Learning for Semantic Parsing}, author={Raymond J. Mooney}, booktitle={Computational Linguistics and Intelligent Text Processing: Proceedings of the 8th International Conference (CICLing 2007)}, month={February}, editor={A. Gelbukh}, address={Mexico City, Mexico}, publisher={Springer: Berlin, Germany}, pages={311--324}, note={Invited paper}, url="http://www.cs.utexas.edu/users/ai-lab?mooney:cicling07", year={2007} }