Paper: Discriminative Reranking For Semantic Parsing

ACL ID P06-2034
Title Discriminative Reranking For Semantic Parsing
Venue Annual Meeting of the Association of Computational Linguistics
Session Poster Session
Year 2006

Semantic parsing is the task of mapping natural language sentences to complete formal meaning representations. The per- formance of semantic parsing can be po- tentially improved by using discrimina- tive reranking, which explores arbitrary global features. In this paper, we investi- gate discriminative reranking upon a base- line semantic parser, SCISSOR, where the composition of meaning representations is guided by syntax. We examine if features used for syntactic parsing can be adapted for semantic parsing by creating similar semantic features based on the mapping between syntax and semantics. We re- port experimental results on two real ap- plications, an interpreter for coaching in- structions in robotic soccer and a natural- language database interface. The results show that rerankin...