This talk discusses our ongoing research at MITRE on “Reading, Learning, Teaching.” This project is addressing a three-stage grand challenge application for human language technology: building a system that can “learn to read”, then “read to learn” and finally “teach to learn.” We have approached this problem through the challenge of Reading Comprehension: building a system that can take and pass successively more difficult reading comprehension tests of the kind routinely used to evaluate human language skills. The talk describes our current system, several data sets that we have prepared to evaluate reading comprehension systems, and a prototype system where a student and the system can interact, with either the system or the student asking and answering questions.

Download Full Presentation