Title :
The method of building expectation model in task-oriented dialogue systems and its realization algorithms
Author :
Liu, Bei ; Du, Limin ; Yu, Shuiyuan
Author_Institution :
Nat. Lab. of Pattern Recognition, Chinese Acad. of Sci., Beijing, China
Abstract :
In human-machine interaction, an effective way to improve the accuracy of semantic analysis is to deduce the users´ intentions by setting expectations. We mainly illustrate how to extract common structures and processing methods of the expectation model (EM) from a scene-specified expectation setting. We then propose algorithms for building and applying EM in spoken dialogue systems. By analyzing the characteristics of system task structure, our algorithms can be used to generate appropriate expectations. After incorporation into the dialogue context, the EM can help create a more reasonable dialogue situation, which endows the system with the preliminary ability to deduce users´ intentions by reference to this situation, so as to improve the robustness of semantic analysis and the transaction-success rate.
Keywords :
human computer interaction; interactive systems; natural language interfaces; speech-based user interfaces; algorithms; expectation model; human-machine interactions; semantic analysis; spoken dialogue systems; task-oriented dialogue systems; Algorithm design and analysis; Buildings; Character recognition; Data structures; Laboratories; Man machine systems; Natural languages; Pattern recognition; Speech analysis; Speech recognition;
Conference_Titel :
Natural Language Processing and Knowledge Engineering, 2003. Proceedings. 2003 International Conference on
Conference_Location :
Beijing, China
Print_ISBN :
0-7803-7902-0
DOI :
10.1109/NLPKE.2003.1275890