Abstract
We describe Scusi?, a multi-stage, spoken language interpretation mechanism designed to be part of a robotmounted dialogue system. Scusi? 's interpretation process maps spoken utterances to conceptual graphs, and the nodes in these graphs to concepts in the world. Maximum posterior probability is used to rank the (partial) interpretations produced at each stage of this process. We show how the features of our interpretation process yield desirable behaviours that support robust and flexible system performance.
| Original language | English |
|---|---|
| Title of host publication | CIMCA 2006 |
| Subtitle of host publication | International Conference on Computational Intelligence for Modelling, Control and Automation, Jointly with IAWTIC 2006: International Conference on Intelligent Agents Web Technologies ... |
| DOIs | |
| Publication status | Published - 1 Dec 2007 |
| Event | CIMCA 2006: International Conference on Computational Intelligence for Modelling, Control and Automation, Jointly with IAWTIC 2006: International Conference on Intelligent Agents Web Technologies and International Commerce - Sydney, NSW, Australia Duration: 28 Nov 2006 → 1 Dec 2006 |
Conference
| Conference | CIMCA 2006: International Conference on Computational Intelligence for Modelling, Control and Automation, Jointly with IAWTIC 2006: International Conference on Intelligent Agents Web Technologies and International Commerce |
|---|---|
| Country | Australia |
| City | Sydney, NSW |
| Period | 28/11/06 → 1/12/06 |
Cite this
}
Probabilistic, multi-staged interpretation of spoken utterances. / Zukerman, Ingrid; Niemann, Michael; George, Sarah.
CIMCA 2006: International Conference on Computational Intelligence for Modelling, Control and Automation, Jointly with IAWTIC 2006: International Conference on Intelligent Agents Web Technologies .... 2007. 4052811.Research output: Chapter in Book/Report/Conference proceeding › Conference Paper › Research › peer-review
TY - GEN
T1 - Probabilistic, multi-staged interpretation of spoken utterances
AU - Zukerman, Ingrid
AU - Niemann, Michael
AU - George, Sarah
PY - 2007/12/1
Y1 - 2007/12/1
N2 - We describe Scusi?, a multi-stage, spoken language interpretation mechanism designed to be part of a robotmounted dialogue system. Scusi? 's interpretation process maps spoken utterances to conceptual graphs, and the nodes in these graphs to concepts in the world. Maximum posterior probability is used to rank the (partial) interpretations produced at each stage of this process. We show how the features of our interpretation process yield desirable behaviours that support robust and flexible system performance.
AB - We describe Scusi?, a multi-stage, spoken language interpretation mechanism designed to be part of a robotmounted dialogue system. Scusi? 's interpretation process maps spoken utterances to conceptual graphs, and the nodes in these graphs to concepts in the world. Maximum posterior probability is used to rank the (partial) interpretations produced at each stage of this process. We show how the features of our interpretation process yield desirable behaviours that support robust and flexible system performance.
UR - http://www.scopus.com/inward/record.url?scp=38849142656&partnerID=8YFLogxK
U2 - 10.1109/CIMCA.2006.165
DO - 10.1109/CIMCA.2006.165
M3 - Conference Paper
SN - 0769527310
SN - 9780769527314
BT - CIMCA 2006
ER -