This study employs a knowledge intensive corpus analysis to identify the elements of the communicative context which can be used to determine the appropriate lexical and grammatic...
Finite-state transducers give efficient representations of many Natural Language phenomena. They allow to account for complex lexicon restrictions encountered, without involving t...
We consider the question of whether or not a successful attempt to simulate human (rational) thought on a computer can contribute to our understanding of the mind, including perha...
A simple and general method is described that can combine different knowledge sources to reorder N-best lists of hypotheses produced by a speech recognizer. The method is automati...
Manny Raynez, David Carter, Vassilios Digalakis, P...
This paper studies the convergence properties of the well known K-Means clustering algorithm. The K-Means algorithm can be described either as a gradient descent algorithmor by sl...