Abstract:

ALICE is a multi-media framework for ICALI programs that is being developed at Carnegie Mellon University. It is not a single instructional program, but rather a set of tools for building a number of different types of ICALI programs in any language. The central components of ALICE are (1) a set of Natural Language Processing (NLP) tools for syntactic error detection, morphological analysis, and generation of morphological paradigms, (2) a set of on-line text, video, and audio corpora that serve as sources of realistic, in-context examples, and (3) an authoring language that allows teachers to configure the NLP tools and excerpts from the corpora into ICALI programs. This paper describes the NLP components of ALICE and the role of excerpts from corpora in treating student errors.

Author: Lori S. Levin, David A. Evans, Donna M. Gates