This paper presents a suite of methods and results for the semantic disambiguation of WordNet glosses. WordNet is a resource widely used in natural language processing and artific...
Recently various techniques to improve the correlation model of feature vector elements in speech recognition systems have been proposed. Such techniques include semi-tied covaria...
We propose new methods to exploit contemporaneous text, such as on-line news articles, to improve language models for automatic speech recognition and other natural language proce...
This article describes an algorithm called HyperLex that is capable of automatically determining word uses in a textbase without recourse to a dictionary. The algorithm makes use ...
We report work on the first component of a two stage speech recognition architecture based on phonological features rather than phones. The paper reports experiments on three phon...