Informational characterization of dialogue states
暂无分享,去创建一个
We introduce multidimensional feature structures as a generalization of standard slot/filler representations commonly employed in spoken language dialogue systems. Nodes in multidimensional feature structures contain an n dimensional vector of values instead of one single filler element. The additional elements serve to represent, among other information, confidence measures of speech recognizers or the number of times a filler has been queried. We demonstrate the application of multidimensional feature structures to spoken dialogue systems. We show that unification based dialogue processing can be retained as long as the elements of the fillers are drawn from partially ordered sets. The dialogue manager employs a variant of constraint logic programming for representing dialogue strategies and update rules. The constraint logic program partitions the space of possible dialogue states in sets of states that are equivalent for the dialogue strategy.
[1] Alexander H. Waibel,et al. Dialogue strategies guiding users to their communicative goals , 1997, EUROSPEECH.
[2] Wayne H. Ward. Extracting information in spontaneous speech , 1994, ICSLP.
[3] Allen L. Gorin,et al. Construct Algebra: Analytical Dialog Management , 1999, ACL.
[4] M. David Sadek,et al. An efficient data-driven model for cooperative spoken dialogue , 1994, ICSLP.
[5] Salim Roukos,et al. Free-flow dialog management using forms , 1999, EUROSPEECH.