The normal practice of selecting relevant documents for training routing queries is to either use all relevants or the 'best n' of them after a (retrieval) ranking opera...
Recently we have begun to build the basic tools for a generic speech-dialog system. The main modules, their function and internal communication have been specified. The different ...
The goal of Information Extraction tasks is to identify, categorize, classify, relate, and normalize specific information of interest found in free text, and to make that informat...
We present an integrated approach to speech and natural language processing which uses a single parser to create training for a statistical speech recognition component and for in...
The output of handwritten word recognizers (WR) tends to be very noisy due to various factors. In order to compensate for this behaviour, several choices of the WR must be initial...
This paper introduces a class of statistical mechanisms, called hidden understanding models, for natural language processing. Much of the framework for hidden understanding models...
Scott Miller, Richard M. Schwartz, Robert J. Bobro...
We show how the recognition performance of a speech recognition component in a speech retrieval system affects the retrieval effectiveness. A speech retrieval system facilitates c...