We present a novel discriminative training algorithm for n-gram language models for use in large vocabulary continuous speech recognition. The algorithm uses large margin estimati...
This paper describes discriminative language modeling for a large vocabulary speech recognition task. We contrast two parameter estimation methods: the perceptron algorithm, and a...
Chrobak (1986) proved that a language accepted by a given nondeterministic finite automaton with one-letter alphabet, i.e., a unary NFA, with n states can be represented as the uni...
This paper investigates the class of TreeTuple MCTAG with Shared Nodes, TTMCTAG for short, an extension of Tree Adjoining Grammars that has been proposed for natural language proc...
The purpose of this paper is to characterize a constituent boundary parsing algorithm, using an information-theoretic measure called generalized mutual information, which serves a...