In this paper we discuss our work on plan management in the Autominder cognitive orthotic system. Autominder is being designed as part of an initiative on the development of roboti...
Martha E. Pollack, Colleen E. McCarthy, Sailesh Ra...
The problem of managing the evolution of complex and large software systems is well known. Evolution implies reuse and modification of existing software artifacts, and this means t...
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...
The creation of a complex web site is a thorny problem in user interface design. First, di erent visitors have distinct goals. Second, even a single visitor may have di erent need...
Corpus-based methods for natural language processing often use supervised training, requiring expensive manual annotation of training corpora. This paper investigates methods for ...