Policy gradient approaches are a powerful instrument for learning how to interact with the environment. Existing approaches have focused on propositional and continuous domains on...
Semi-supervised learning (SSL), is classification where additional unlabeled data can be used to improve accuracy. Generative approaches are appealing in this situation, as a mode...
Hierarchical phrase-based models provide a powerful mechanism to capture non-local phrase reorderings for statistical machine translation (SMT). However, many phrase reorderings a...
Understanding the sequence-to-structure relationship is a central task in bioinformatics research. Adequate knowledge about this relationship can potentially improve accuracy for ...
Wei Zhong, Jieyue He, Robert W. Harrison, Phang C....
Ranking plays a central role in many Web search and information retrieval applications. Ensemble ranking, sometimes called meta-search, aims to improve the retrieval performance b...