Dialogue Processing with Neural Networks

This paper describes a novel connectionist system for dialogue processing. Based on a script-like formalism, the system consists of several modular neural networks which can track the semantic flow of a dialogue. The system can be extended to understand and translate dialogues in a fixed domain. This research was partially supported by ATR Interpreting Telephony Research Laboratories, NEC and Siemens. The views and conclusions contained in this document are those of the authors and should not be interpreted as representing the official policies, either expressed or implied, of the ATR, NEC or Siemens.