If I Have a Hammer: Computational Linguistics in a Reading Tutor that Listens - Robotics Institute Carnegie Mellon University

If I Have a Hammer: Computational Linguistics in a Reading Tutor that Listens

Conference Paper, Proceedings of 42nd Annual Meeting of the Association of Computational Linguistics (ACL-EACL '04), July, 2004

Abstract

Project LISTEN?s Reading Tutor uses speech recognition to listen to children read aloud, and helps them learn to read, as evidenced by rigorous evaluations of pre- to posttest gains compared to various controls. In the 2003-2004 school year, children ages 5-14 used the Reading Tutor daily at school on over 200 computers, logging over 50,000 sessions, 1.5 million tutorial responses, and 10 million words. This talk uses the Reading Tutor to illustrate the diverse roles that computational linguistics can play in an intelligent tutor: A domain model describes a skill to learn, such as mapping from spelling to pronunciation. A production model predicts student behavior, such as likely oral reading mistakes. A language model predicts likely word sequences for a given task, such as oral reading. A student model estimates a student?s skills, such as mastery of grapheme-to-phoneme mappings. A pedagogical model guides tutorial decisions, such as choosing words a student is ready to try. A recurring theme is the use of ?big data? to train such models automatically.

Notes
Invited keynote address

BibTeX

@conference{Mostow-2004-8983,
author = {Jack Mostow},
title = {If I Have a Hammer: Computational Linguistics in a Reading Tutor that Listens},
booktitle = {Proceedings of 42nd Annual Meeting of the Association of Computational Linguistics (ACL-EACL '04)},
year = {2004},
month = {July},
}