MRE: A Study on Evolutionary Language Understanding (bibtex)
by Feng, Donghui and Hovy, Eduard
Abstract:
The lack of well-annotated data is always one of the biggest problems for most training-based dialogue systems. Without enough training data, it's almost impossible for a trainable system to work. In this paper, we explore the evolutionary language understanding approach to build a natural language understanding machine in a virtual human training project. We build the initial training data with a finite state machine. The language understanding system is trained based on the automated data first and is improved as more and more real data come in, which is proved by the experimental results.
Reference:
MRE: A Study on Evolutionary Language Understanding (Feng, Donghui and Hovy, Eduard), In Second International Workshop on Natural Language Understanding and Cognitive Science (NLUCS), 2005.
Bibtex Entry:
@inproceedings{feng_mre:_2005,
	address = {Miami, Florida},
	title = {{MRE}: {A} {Study} on {Evolutionary} {Language} {Understanding}},
	url = {http://ict.usc.edu/pubs/MRE-%20A%20Study%20on%20Evolutionary%20Language%20Understanding.pdf},
	abstract = {The lack of well-annotated data is always one of the biggest problems for most training-based dialogue systems. Without enough training data, it's almost impossible for a trainable system to work. In this paper, we explore the evolutionary language understanding approach to build a natural language understanding machine in a virtual human training project. We build the initial training data with a finite state machine. The language understanding system is trained based on the automated data first and is improved as more and more real data come in, which is proved by the experimental results.},
	booktitle = {Second {International} {Workshop} on {Natural} {Language} {Understanding} and {Cognitive} {Science} ({NLUCS})},
	author = {Feng, Donghui and Hovy, Eduard},
	month = may,
	year = {2005}
}
Powered by bibtexbrowser