History of Knowledge and Processes for Spoken Language Understanding
Renato De Mori · 2011
This chapter reviews the evolution of methods for spoken language understanding (SLU) systems. It provides Meaning Representation Language (MRL) with methods for obtaining meaning representations from natural language. The chapter introduces probabilistic frameworks accounting for knowledge imprecision and limitations of automatic speech recognition systems. It reviews automatic systems for SLU using these methods. Computer epistemology deals with the representation of semantic knowledge in a computer using an appropriate formalism. Furthermore, especially for SLU, signs used for interpretation are extracted from the speech signal with a process that is not perfect. These problems suggested the use of probabilistic models and machine learning methods for automatically characterizing supports for semantic constituents end their relations. As a consequence, methods were proposed for estimating the parameters of generative models and classification methods. The chapter reviews these methods, and reports some evaluations. Controlled Vocabulary Terms natural language processing; speech recognition equipment