In this paper we investigate a maximum entropy approach to spoken language under standing. We compare this approach with a parser based on finite-state transducers. The parsers are evaluated on a corpus of utterances modelling human-computer interactions within a single domain. The corpus was annotated with task-oriented semantic categories to obtain a set of shallow functional parse trees. We focus our investigation on the quality of the structured concepts produced by each approach. A direct comparison shows that the maximum entropy parser achieves better performance than the finite-state parser, even with very limited training data.