Augmenting Conversational Characters with Generated Question-Answer Pairs (bibtex)
by Nouri, Elnaz, Artstein, Ron, Leuski, Anton and Traum, David
Abstract:
We take a conversational character trained on a set of linked question-answer pairs authored by hand, and augment its training data by adding sets of question-answer pairs which are generated automatically from texts on different topics. The augmented characters can answer questions about the new topics, at the cost of some performance loss on ques- tions about the topics that the original character was trained to answer.
Reference:
Augmenting Conversational Characters with Generated Question-Answer Pairs (Nouri, Elnaz, Artstein, Ron, Leuski, Anton and Traum, David), In AAAI Symposium on Question Generation, 2011.
Bibtex Entry:
@inproceedings{nouri_augmenting_2011,
	address = {Arlington, VA},
	title = {Augmenting {Conversational} {Characters} with {Generated} {Question}-{Answer} {Pairs}},
	url = {http://ict.usc.edu/pubs/Augmenting%20Conversational%20Characters%20with%20Generated%20Question-Answer%20Pairs.pdf},
	abstract = {We take a conversational character trained on a set of linked question-answer pairs authored by hand, and augment its training data by adding sets of question-answer pairs which are generated automatically from texts on different topics. The augmented characters can answer questions about the new topics, at the cost of some performance loss on ques- tions about the topics that the original character was trained to answer.},
	booktitle = {{AAAI} {Symposium} on {Question} {Generation}},
	author = {Nouri, Elnaz and Artstein, Ron and Leuski, Anton and Traum, David},
	month = nov,
	year = {2011},
	keywords = {Virtual Humans},
	pages = {49--52}
}
Powered by bibtexbrowser