DocumentCode
394248
Title
Graph-based representation and techniques for NLU application development
Author
Huerta, J.M. ; Lubensky, David
Author_Institution
IBM T. J. Watson Res. Center, Yorktown Heights, NY, USA
Volume
1
fYear
2003
fDate
6-10 April 2003
Abstract
We describe a method to represent, manipulate, structure and aid in the design and development of NLU oriented parsers. Our method is based on the representation of the semantic parser domain into a single directed graph showing the parser´s labels and their immediate inter-relationships as they exist in the annotated development corpora. Furthermore, we present methods developed around this representation illustrating how, a developer can visualize, manipulate, design and construct new applications simply by acting on the domain graph and sub-graphs. We also describe how the graph representation method can be utilized in the reduction of the complexity of the parser by identification and removal of nodes, edges and structures of the domain graph whose impact on attribute accuracy is small. We present the following examples of applications of our technique: extension of an existing air travel information domain to include car rental reservation by manipulating the corresponding graphs, structuring such graphs´ vertices into 3-tiers, an example of a method for complex domain decomposition into simpler sub-graphs, and experiments on the reduction of a parser´s complexity. Our technique can serve as a foundation of GUI toolkits for NLU development built around these concepts.
Keywords
directed graphs; graphical user interfaces; natural language interfaces; natural languages; speech processing; speech recognition; GUI toolkits; NLU application development; NLU oriented parsers; air travel information; annotated development corpora; car rental reservation; complex domain decomposition; dialog-based automatic speech understanding; directed graph; domain graph; domain sub-graphs; edges identification; edges removal; graph representation method; graph-based representation; natural language understanding; nodes identification; nodes removal; parser complexity reduction; parser labels; semantic parser domain representation; Humans; Information representation; Labeling; Natural languages; Speech; Statistical analysis; Telephony; Training data; Tree graphs; Visualization;
fLanguage
English
Publisher
ieee
Conference_Titel
Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03). 2003 IEEE International Conference on
ISSN
1520-6149
Print_ISBN
0-7803-7663-3
Type
conf
DOI
10.1109/ICASSP.2003.1198774
Filename
1198774
Link To Document