We introduce a learning semantic parser, Scissor, that maps natural-language sentences to a detailed, formal, meaning-representation language. It first uses an integrated statistical parser to produce a semantically augmented parse tree, in which each non-terminal node has both a syntactic and a semantic label. A compositional-semantics procedure is then used to map the augmented parse tree into a final meaning representation. We evaluate the system in two domains, a natural-language database interface and an interpreter for coaching instructions in robotic soccer. We present experimental results demonstrating that Scissor produces more accurate semantic representations than several previous approaches.

PDF, PS

In Proceedings of CoNLL-2005, Ann Arbor, Michigan, June 2005.

@InProceedings{ge:conll05, title={A Statistical Semantic Parser that Integrates Syntax and Semantics}, author={Ruifang Ge and Raymond J. Mooney}, booktitle={Proceedings of CoNLL-2005}, month={June}, address={Ann Arbor, Michigan}, url="http://www.cs.utexas.edu/users/ai-lab?ge:conll05", year={2005} }