Perceptron training is widely applied in the natural language processing community for learning complex structured models. Like all structured prediction learning frameworks, the ...
Conventional sentence compression methods employ a syntactic parser to compress a sentence without changing its meaning. However, the reference compressions made by humans do not ...
An argument by Kratzer (2000) based on Schein (1986, 1993) does not conclusively show that events and thematic roles are necessary ingredients of the logical representation of natu...
Convergence is often the key liveness property for distributed systems that interact with physical processes. Techniques for proving convergence (asymptotic stability) have been ex...
Geospatial information services composition is a promising approach to construct complex Web GIS applications. BPEL, which is the language and the industry standard that expresses ...