8th International Conference on Spoken Language Processing

Jeju Island, Korea
October 4-8, 2004

A Robust Understanding Model for Spoken Dialogues

Junyan Chen, Ji Wu, Zuoying Wang

Tsinghua University, China

This paper presents a robust model for language understanding in spoken dialogue systems, in which the understanding problem is formulated as a three-stage process. In the first stage, semantic concepts included in the utterance are identified through a bottom-up chart parser to build a concept graph. Then, in the second stage, communicative goal of each candidate path searched from the concept graph is determined by a classifier based on latent semantic analysis. Finally, information of discourse history is introduced to guide the search in all hypotheses for the best result. Experiments with a test set composed of spontaneous utterances show that this model outperforms a rule-based model by 8.1% and 21.5% in goal and concept understanding respectively, which proves its advantage to robust spontaneous language understanding.

Full Paper

Bibliographic reference.  Chen, Junyan / Wu, Ji / Wang, Zuoying (2004): "A robust understanding model for spoken dialogues", In INTERSPEECH-2004, 589-592.