Automating the construction of semantic grammars is a difficult and interesting problem for machine learning. This paper shows how the semantic-grammar acquisition problem can be viewed as the learning of search-control heuristics in a logic program. Appropriate control rules are learned using a new first-order induction algorithm that automatically invents useful syntactic and semantic categories. Empirical results show that the learned parsers generalize well to novel sentences and out-perform previous approaches based on connectionist techniques.
In Proceedings of the 11th National Conference on Artificial Intelligence, pp. 817-822 1993. Menlo Park, CA: AAAI Press.

Raymond J. Mooney Faculty mooney [at] cs utexas edu
John M. Zelle Ph.D. Alumni john zelle [at] wartburg edu