HIERARCHICAL TAG-GRAPH SEARCH FOR SPONTANEOUS SPEECH UNDERSTANDING IN SPOKEN DIALOG SYSTEMS
Journal
5th International Conference on Spoken Language Processing, ICSLP 1998
Date Issued
1998
Author(s)
Abstract
It has been relatively difficult to develop natural language parsers for spoken dialog systems, not only because of the possible recognition errors, pauses, hesitations, out-of-vocabulary words, and the grammatically incorrect sentence structures, but because of the great efforts required to develop a general enough grammar with satisfactory coverage and flexibility to handle different applications. In this paper, a new hierarchical graph-based search scheme with layered structure is presented, which is shown to provide more robust and flexible spontaneous speech understanding for spoken dialog systems. © 1998. 5th International Conference on Spoken Language Processing, ICSLP 1998. All rights reserved.
Other Subjects
Computational linguistics; Hierarchical systems; Natural language processing systems; Speech recognition; Syntactics; Graph search; Graph-based; Hierarchical graphs; Natural languages; Outof-vocabulary words (OOV); Recognition error; Sentence structures; Speech understanding; Spoken dialogue system; Spontaneous speech; Graphic methods
Type
conference paper