Paper: Semantic Parsing as Machine Translation

ACL ID P13-2009
Title Semantic Parsing as Machine Translation
Venue Annual Meeting of the Association of Computational Linguistics
Session Short Paper
Year 2013

Semantic parsing is the problem of de- riving a structured meaning representation from a natural language utterance. Here we approach it as a straightforward ma- chine translation task, and demonstrate that standard machine translation com- ponents can be adapted into a semantic parser. In experiments on the multilingual GeoQuery corpus we find that our parser is competitive with the state of the art, and in some cases achieves higher accu- racy than recently proposed purpose-built systems. These results support the use of machine translation methods as an infor- mative baseline in semantic parsing evalu- ations, and suggest that research in seman- tic parsing could benefit from advances in machine translation.