DocumentCode
454627
Title
Learning Edit Machines for Robust Multimodal Understanding
Author
Johnston, Michael ; Bangalore, Srinivas
Author_Institution
AT&T Labs-Res., Florham Park, NJ
Volume
1
fYear
2006
fDate
14-19 May 2006
Abstract
Multimodal grammars provide an expressive formalism for multimodal integration and understanding. However, hand-crafted multimodal grammars can be brittle with respect to unexpected, erroneous, or disfluent inputs. In previous work, we have shown how the robustness of stochastic language models can be combined with the expressiveness of multimodal grammars by adding a finite-state edit machine to the multimodal language processing cascade. In this paper, we present an approach where the edits are trained from data using a noisy channel model paradigm. We evaluate this model and compare its performance against hand-crafted edit machines from our previous work in the context of a multimodal conversational system (MATCH)
Keywords
language translation; natural languages; finite-state edit machine; learning edit machines; multimodal grammars; noisy channel model paradigm; robust multimodal understanding; stochastic language models; Cities and towns; Context modeling; Graphics; Lattices; Machine learning; Natural languages; Robustness; Speech processing; Stochastic processes; Transducers;
fLanguage
English
Publisher
ieee
Conference_Titel
Acoustics, Speech and Signal Processing, 2006. ICASSP 2006 Proceedings. 2006 IEEE International Conference on
Conference_Location
Toulouse
ISSN
1520-6149
Print_ISBN
1-4244-0469-X
Type
conf
DOI
10.1109/ICASSP.2006.1660096
Filename
1660096
Link To Document