This paper gives an overview of our spoken dialogue system, which is design
ed to meet four objectives, Portability, Usability, Robustness, and Extensi
bility (PURE). First, an integrated scoring function is proposed so that al
l components of the spoken dialogue system can be properly integrated, and
information from all components can be considered jointly to resolve ambigu
ities. Moreover, instead of shallow analysis or simply keyword/key-phrase m
atching, deeper analysis is conducted by incorporating robust parsing, erro
r recovery and semantic analysis to improve discrimination and robustness o
f the language understanding component. To achieve PURE design of dialogue
management, a domain transparent framework is also proposed in this paper.
Results and experiences we got from building systems of various domains sho
wed very encouraging results.