Active learning has been proven a reliable strategy to reduce manual efforts in training data labeling. Such strategies incorporate the user as oracle: the classifier selects the m...
We present new results from a real-user evaluation of a data-driven approach to learning user-adaptive referring expression generation (REG) policies for spoken dialogue systems. ...
TransType2 is a novel kind of interactive MT in which the system and the user collaborate in drafting a target text, the system’s contribution taking the form of predictions that...
This paper describes ActionStreams, a system for inducing task models from observations of user activity. The model can represent several task structures: hierarchy, variable sequ...
The metaDESK is a user interface platform demonstrating new interaction techniques we call “tangible user interfaces.” We explore the physical instantiation of interface eleme...