Translation of proper names is generally recognized as a significant problem in many multi-lingual text and speech processing applications. Even when large bilingual lexicons use...
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...
Interfaces based on recognition technologies are used extensively in both the commercial and research worlds. But recognizers are still error-prone, and this results in human perf...
Jennifer Mankoff, Scott E. Hudson, Gregory D. Abow...
A new approach to the recognition of temporal behaviors and activities is presented. The fundamental idea, inspired by work in speech recognition, is to divide the inference probl...
The current expansion in collections of natural language based digital documents in various media and languages is creating challenging opportunities for automatically accessing t...