Find in Library

Most information systems that deal with natural language texts do not tolerate much deviation from their idealized and simplified model of language. Spoken dialog is notoriously ungrammatical however. Because the MAREDI project focuses in particular on the automatic analysis of scripted dialogs, we needed to develop a robust capacity to analyze transcribed spoken language. This paper presents the main elements of our approach, which is based on exploiting surface markers as the best route to the semantics of the conversation modelled. We highlight the foundations of our particular conversational model and give an overview of the MAREDI system. The latter consists of three key modules, which are 1) a connectionist network to recognise speech acts, 2) a robust syntactic parser, and 3) a semantic analyzer. These three modules are fully implemented in Prolog and C++ and have been packaged into an integrated software.