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...
It is well known that pragmatic knowledge is useful and necessary in many difficult language processing tasks, but because this knowledge is difficult to acquire and process autom...
The paper presents two models for producing and understanding situationally appropriate referring expressions (REs) during a discourse about large-scale space. The models are eval...
Hendrik Zender, Christopher Koppermann, Fai Greeve...
The paper describes the design of a generation component for a spoken dialogue system. After discussing three existing models of generation, a model based on new information focus...
We present a syllable bigram model for segmenting a Korean sentence into words and correcting word-spacing errors in the spelling checker. We evaluated the system’s performance ...