CIS Department Talk - November 12, 2009
The Department of Computer and Information Science Presents
|Speaker:|| Dr. Joel Tetreault, Educational Testing Service (ETS)
|Topic:||Automated Essay Scoring and ESL Error Detection
|Date:||November 12, 2009|
|Place:||John Mulcahy Hall, Room 112|
While standardized testing has been in place for over 50 years now, one of the largest changes to the practice has come in the last ten with the use of Natural Language Processing techniques to automatically score student essays with levels of agreement with a human rater that are comparable to those found between two human raters. In this talk, we will first provide an overview of the automated essay scoring engine (e-rater) used at Educational Testing Service for the TOEFL and GRE. Next, we will discuss the development of one of e-rater's newest components: a module to detect preposition errors in student writing, an error that is particularly problematic for students learning English as a second language.
Joel Tetreault is an associate research scientist specializing in Computational Linguistics in the Research & Development Division at Educational Testing Service in Princeton, NJ. His research focus is Natural Language Processing with specific interests in anaphora, dialogue and discourse processing, machine learning, and applying these techniques to the analysis of English language learning and automated essay scoring. Currently he is working on automated methods for detecting grammatical errors by non-native speakers, plagiarism detection, and content scoring methods. Previously, he was a
Postdoctoral research scientist at the University of Pittsburgh's Learning Research and Development Center (2004-2007). There he worked on developing spoken dialogue tutoring systems. Tetreault received his B.A. in Computer Science from Harvard University (1998) and his M.S. and Ph.D. in Computer Science from the University of Rochester (2004).