We attemped to improve recognition accuracy by reducing the inadequacies of the lexicon and language model. Specifically we address the following three problems: (1) the best size...
Richard M. Schwartz, Long Nguyen, Francis Kubala, ...
A method is presented that uses an Approximate Nearest Neighbor method for determining correspondences within the Iterative Closest Point Algorithm. The method is based upon the k...
Most decision tree induction methods used for extracting knowledge in classification problems are unable to deal with uncertainties embedded within the data, associated with human...
We describe an effective constituent projection strategy, where constituent projection is performed on the basis of dependency projection. Especially, a novel measurement is propo...
We propose a type system based on regular tree grammars, where algebraic datatypes are interpreted in a structural way. Thus, the same constructors can be reused for different typ...