There were three GREC Tasks at Generation Challenges 2010: GREC-NER required participating systems to identify all people references in texts; for GRECNEG, systems selected corefe...
—Most Web and legacy paper-based documents are available in human comprehensible text form, not readily accessible to or understood by computer programs. Here, we investigate an ...
For centuries, scholars have explored the deep links among human languages. In this paper, we present a class of probabilistic models that use these links as a form of naturally o...
Recent research in Augmented and Alternative Communication (AAC) has begun to make use of Natural Language Generation (NLG) techniques. This creates an opportunity for constructin...
While human tutors typically interact with students using spoken dialogue, most computer dialogue tutors are text-based. We have conducted two experiments comparing typed and spoke...