Supervised sequence-labeling systems in natural language processing often suffer from data sparsity because they use word types as features in their prediction tasks. Consequently...
A significant portion of the world's text is tagged by readers on social bookmarking websites. Credit attribution is an inherent problem in these corpora because most pages h...
Daniel Ramage, David Hall, Ramesh Nallapati, Chris...
A novel method for the segmentation of double-sided ancient document images suffering from bleed-through effect is presented. It takes advantage of the level set framework to prov...
—In this paper, we propose a novel method for extracting handwritten characters from multi-language document images, which may contain various types of characters, e.g. Chinese, ...
Yonghong Song, Guilin Xiao, Yuanlin Zhang, Lei Yan...
We have already proposed using evolutionary computation to adjust the voice quality conversion parameters, and we have reported that this approach produces results that are not onl...