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...
A word in one language can be translated to zero, one, or several words in other languages. Using word fertility features has been shown to be useful in building word alignment mo...
Robust Spoken Language Understanding (SLU) is a key component of spoken dialogue systems. Recent statistical approaches to this problem require additional resources (e.g. gazettee...
Hidden Markov models play a critical role in the modelling and problem solving of important AI tasks such as speech recognition and natural language processing. However, the stude...
As more and more information is available in the Electronic Health Record in the form of free-text narrative, there is a need for automated tools, which can process and understand...