Semantic representations in spoken dialogue systems

In this paper, the requirements on semantic representations in spoken dialogue systems are discussed. It is argued that spoken dialogue needs a special treatment when it comes to natural language processing, since the phenomena that occur in spoken language are not the same as those that occur in written language. These special properties of spoken language are outlined and the different aspects that need to be represented are discussed. The most common semantic formalisms – first-order logic, feature structures and simple frames – are also presented and discussed with respect to these requirements. It is argued that spoken dialogue not just puts further requirements on semantic representations, but that the focus instead should shift away from problems that are mostly common in written language to those that are common in spoken language.