Current corpus-based machine translation techniques do not work very well when given scarce linguistic resources. To examine the gap between human and machine translators, we crea...
Systems that learn from examples often express the learned concept in the form of a disjunctive description. Disjuncts that correctly classify few training examples are known as s...
Communication is an essential and necessary aspect of professional work in science and business. Besides the traditional face to face communication more and more face-file-face co...
This paper proposes a noise robust exemplar-based speech recognition system where noisy speech is modeled as a linear combination of a set of speech and noise exemplars. The metho...
Finite state machines have been used to model a number of classes of system and there has thus been much interest in the automatic generation of test sequences from finite state m...