We desert'be our latest attempt at adaptive language modeling. At the heart of our approachis a Maximum Entropy(ME) modelwhich inc.orlxnatesmanyknowledgesources in a consiste...
We developed a faster search algorithm that avoids the use of the N-Best paradigm until after more powerful knowledge sources have been used. We found, however, that there was lit...
Long Nguyen, Richard M. Schwartz, Ying Zhao, Georg...
This paper describes a method of detecting speechrepairs that uses a part-of-speech tagger. The tagger is given knowledgeabout category transitions for speechrepairs, and sois abl...
This paper presents and evaluates models created according to a schema that provides a description of the joint distribution of the values of sense tags and contextual features th...
We describe the design of Comlex Syntax, a computational lexicon providing detailed syntactic information for approximately 38,000 EnglJish headwords. We consider the types of err...