In this paper we compare two approaches to natural language understanding (NLU). The first approach is derived from the field of statistical machine translation (MT), whereas the other uses the maximum entropy (ME) framework. Starting with an annotated corpus, we describe the problem of NLU as a translation from a source sentence to a formal language target sentence. We mainly focus on the quality of the different alignment and ME models and show that the direct ME approach outperforms the alignment templates method. .
