Tree-based statistical machine translation models have made significant progress in recent years, especially when replacing 1-best trees with packed forests. However, as the parsi...
Hao Xiong, Wenwen Xu, Haitao Mi, Yang Liu, Qun Liu
The recently introduced online confidence-weighted (CW) learning algorithm for binary classification performs well on many binary NLP tasks. However, for multi-class problems CW l...
Contextual reasoning through graphical models such as Markov Random Fields often show superior performance against local classifiers in many domains. Unfortunately, this performanc...
In this paper we study multi-level dynamically reconfigurable architectures. These are extensions of standard reconfigurable architectures where ordinary reconfiguration operation...
It is desirable to find unusual data objects by Ramaswamy et al's distance-based outlier definition because only a metric distance function between two objects is required. It...