In spoken dialogue systems, it is important for a system to know how likely a speech recognition hypothesis is to be correct, so it can reprompt for fresh input, or, in cases wher...
We present three systems for surface natural language generation that are trainable from annotated corpora. The first two systems, called NLG1 and NLG2, require a corpus marked on...
We present a study comparing how people use space in a Tangible User Interface (TUI) and in a Graphical User Interface (GUI). We asked subjects to read ten summaries of recent new...
Withthe proliferationof software agents and smart hardware devices there is a growing realization that large-scale problems can be addressed by integration of such standalone syst...
We classify and review current approaches to software infrastructure for research, development and delivery of NLP systems. The task is motivated by a discussion of current trends...
Hamish Cunningham, Kevin Humphreys, Robert J. Gaiz...