Traditionally, text classifiers are built from labeled training examples. Labeling is usually done manually by human experts (or the users), which is a labor intensive and time co...
Information Extraction methods can be used to automatically "fill-in" database forms from unstructured data such as Web documents or email. State-of-the-art methods have...
Trausti T. Kristjansson, Aron Culotta, Paul A. Vio...
We describe SCoT, a Spoken Conversational Tutor, which has been implemented in order to investigate the advantages of natural language in tutoring, especially spoken language. SCo...
Karl Schultz, Brady Clark, Heather Pon-Barry, Eliz...
Local search algorithms are one of the effective methods for solving hard combinatorial problems. However, a serious problem of this approach is that the search often traps at loca...
The long-term goal of Project Halo is to build an application called Digital Aristotle that can answer questions on a variety of science topics and provide user and domain appropr...
Ken Barker, Vinay K. Chaudhri, Shaw Yi Chaw, Peter...