Robust parsing of spoken dialogue using contextual knowledge and recognition probabilities (1995) [22 citations — 1 self]
Download:
|
|
by Gunther Gorz, Gerhard Hanrieder
In ESCA Tutorial and Research Workshop on Spoken Dialogue Systems
http://faui80.informatik.uni-erlangen.de/IMMD8/staff/Goerz/././papersgg/daene.ps.gz
Add To MetaCart
Abstract:
In this paper we describe the linguistic processing component of a spoken dialogue system. The task of this word graph parser is to find the most plausible sequence of word hypotheses in the input graph. If no global solution can be found, a robust mechanism of selecting multiple partial results is applied. We argue that the semantic accuracy of the selected results can be considerably improved if the selection is based on an integrated quality score combining word recognition probabilities and context-dependent semantic top-down predictions. Results of parsing word graphs with and without predictions are reported.
Citations
| 21 | Parsing word graphs using a linguistic grammar and a statistical language model – Schmid - 1994 |
| 17 | Static and Dynamic Predictions: A Method to Improve Speech Understanding in Cooperative Dialogues – Andry - 1992 |
| 7 | Robust analysis and interpretation in speech dialogue – Hanrieder, Heisterkamp - 1994 |
| 7 | A Knowledge Based Speech Understanding System – Niemann, Brietzmann, et al. - 1988 |
| 3 | Robust speech understanding – Brietzmann, Class, et al. - 1994 |
