We present an approach to automatically identifying the arguments of discourse connectives based on data from the Penn Discourse Treebank. Of the two arguments of connectives, cal...
- The classifier built from a data set with a highly skewed class distribution generally predicts the more frequently occurring classes much more often than the infrequently occurr...
In this paper we present an experimental toolbox for automatic tree-to-tree alignment based on local classification and alignment inference. The aligner implements a recurrent arc...
- Even though state-of-the-art FPGAs present new opportunities in exploring low-cost high-performance architectures for floating-point scientific applications, they also pose serio...
Mobile software systems are characterized by their highly dynamic and unpredictable execution context. Such systems are permeating a number of domains where the systems operate in ...