A semantic interpreter and a cooperative response generator for a robust spoken dialogue system

In this paper, we describe a semantic interpreter and a cooperative respons e generator for a multimodal dialogue system which consists of speech input , touch screen input, speech output and graphical output. The dialogue syst em understands spontaneous speech which has many ambiguous phenomena such a s interjections, ellipses, inversions, repairs, unknown words and so on, an d responses to user for the utterance. But some utterances fail to be analy zed. This is caused due to "misrecognition" with the speech recognizer, "in completeness" with the semantic interpreter and "lack of database" with the response generator. Therefore, we improved the semantic interpreter to bui ld a more robust one. If a user's query does not have enough conditions/inf ormation to answer the question with the system, the dialogue manager shoul d query the user to get the necessary conditions or to select the candidate . Further, if the system cannot retrieve any information related to the use r's question, the generator should propose an alternative plan. Based on th ese considerations, we developed a cooperative response generator in the di alogue system. We report the evaluation results of the semantic interpreter and cooperative response generator in our dialogue system.