High-dimensional data usually incur learning deficiencies and computational difficulties. We present a novel semi-supervised dimensionality reduction technique that embeds high-dim...
Abstract—PROGRESS is a project and strategic research centre at M¨alardalen University in Sweden that is funded for 2006– 2010 by the Swedish Foundation for Strategic Research...
Johan Kraft, Holger M. Kienle, Thomas Nolte, Ivica...
Current tree-to-tree models suffer from parsing errors as they usually use only 1best parses for rule extraction and decoding. We instead propose a forest-based tree-to-tree model...