This paper presents PARADISE PARAdigm for DIalogue System Evaluation, a general framework for evaluating and comparing the performance of spoken dialogue agents. The framework d...
Marilyn A. Walker, Diane J. Litman, Candace A. Kam...
Decision-tree algorithms are known to be unstable: small variations in the training set can result in different trees and different predictions for the same validation examples. B...
Corpus-based grammar induction generally relies on hand-parsed training data to learn the structure of the language. Unfortunately, the cost of building large annotated corpora is...
We present our experience using a large, real-world application as a course project for the second half of the semester of a CS2 course. Our primary goal for the project was to cr...
In this paper, we propose a new constructive method, based on cooperative coevolution, for designing automatically the structure of a neural network for classification. Our appro...