tailieunhanh - Báo cáo khoa học: "Context Management with Topics for Spoken Dialogue Systems"

In this paper we discuss the use of discourse context in spoken dialogue systems and argue that the knowledge of the domain, modelled with the help of dialogue topics is important in maintaining robustness of the system and improving recognition accuracy of spoken utterances. We propose a topic model which consists of a domain model, structured into a topic tree, and the Predict-Support algorithm which assigns topics to utterances on the basis of the topic transitions described in the topic tree and the words recognized in the input utterance. . | Context Management with Topics for Spoken Dialogue Systems Kristiina Jokinen and Hideki Tanaka and Akio Yokoo ATR Interpreting Telecommunications Research Laboratories 2-2 Hikaridai Seika-cho Soraku-gun Kyoto 619-02 Japan email kj okinen tanakah ayokoo it 1. atr . Abstract In this paper we discuss the use of discourse context in spoken dialogue systems and argue that the knowledge of the domain modelled with the help of dialogue topics is important in maintaining robustness of the system and improving recognition accuracy of spoken utterances. We propose a topic model which consists of a domain model structured into a topic tree and the Predict-Support algorithm which assigns topics to utterances on the basis of the topic transitions described in the topic tree and the words recognized in the input utterance. The algorithm uses a probabilistic topic type tree and mutual information between the words and different topic types and gives recognition accuracy of and precision of . This makes our topic model highly comparable to discourse models which are based on recognizing dialogue acts. 1 Introduction One of the fragile points in integrated spoken language systems is the erroneous analyses of the initial speech The output of a speech recognizer has direct influence on the performance of other modules of the system dealing with dialogue management translation database search response planning etc. and the initial inaccuracy usually gets accumulated in the later stages of processing. Performance of speech recognizers can be improved by tuning their language model and lexicon but problems still remain with the erroneous ranking of the best paths information content of the selected utterances may be wrong. It is thus essential to use contextual information to compensate various errors in the output to provide expectations of what will be said next and to help to determine the appropriate dialogue state. However negative effects of an inaccurate