This study shows that a mixture of RNN experts model can acquire the ability to generate sequences that are combination of multiple primitive patterns by means of self-organizing ...
Queries describe the users' search intent and therefore they play an essential role in the context of ranking for information retrieval and Web search. However, most of exist...
Many applications in text processing require significant human effort for either labeling large document collections (when learning statistical models) or extrapolating rules from...
This paper explores a recently proposed and rarely reported subspace learning method, Spectral Regression Discriminant Analysis (SRDA) [1, 2], on silhouette based human action rec...
In this paper we present a novel strategy, DragPushing, for improving the performance of text classifiers. The strategy is generic and takes advantage of training errors to succes...
Songbo Tan, Xueqi Cheng, Moustafa Ghanem, Bin Wang...