Och's (2003) minimum error rate training (MERT) procedure is the most commonly used method for training feature weights in statistical machine translation (SMT) models. The u...
Abstract. The approaches previously used for sentence alignment (sentence length, word correspondence and cognate matching) take into account different aspects of similarity betwe...
We describe a neural network which enhances and completes salient closed contours. Our work is different from all previous work in three important ways. First, like the input prov...
One way to handle the perception of images that change in position (or size, orientation or deformation) is to invoke rapidly changing fiber projections to project images into a fi...
Junmei Zhu, Urs Bergmann, Christoph von der Malsbu...
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...