Publications

Advanced search

Abstract

Carlos D. Martínez-Hinarejos, Francisco Casacuberta. A Pattern Recognition Approach to Dialog Labelling by using Finite-State Transducers. Proceedings of 5th. IberoAmerican Symposium on Pattern Recognition, 2000. pp. 669-677.

The dialogue system is a new application of speech recognition and understanding systems, with clear implications for linguistic knowledge. This knowledge is expressed in labels that point out the intention and semantic of the dialog turn of the user and the system. Determining this knowledge can be viewed as a pattern recognition problem: assigning the adequate labels to the turn. The labelling work is a complex task, so, in this work, we present a method for semiautomatic labelling of a dialog based on Finite-State Transducers which are learnt from correctly labeled dialogs. We will show that this tool provides high quality dialog labelling, that makes the labelling task easier for a human expert.