Using a lexicon can often improve character recognition under challenging conditions, such as poor image quality or unusual fonts. We propose a flexible probabilistic model for c...
Jerod J. Weinman, Erik G. Learned-Miller, Allen R....
Self-training is a semi-supervised learning algorithm in which a learner keeps on labeling unlabeled examples and retraining itself on an enlarged labeled training set. Since the s...
Complexity is often hypothesized to be the enemy of software security. If this hypothesis is true, complexity metrics may be used to predict the locale of security problems and ca...
We apply the hypothesis of "One Sense Per Discourse" (Yarowsky, 1995) to information extraction (IE), and extend the scope of "discourse" from one single docum...
In this paper, we present a Question Answering system called KUQA (Korea University Question Answering system) developed by using semantic categories and co-occurrence density. Se...
Soo-Min Kim, Dae-Ho Baek, Sang-Beom Kim, Hae-Chang...