From The Theme
LEARNING AND TRAINING

WHAT IF
What if language learners could practice conversation with a computerized system capable of offering feedback and evaluation?

WHAT WE SET OUT TO DO
We set out to develop a natural language processing engine to help language learners practice conversation. The engine needed to be robust when interpreting input, but precise when doing analysis and responding to the student. The goal was to develop an interface that would enable the system to figure out what the student wants to say, and present the necessary corrections.

WHAT WE FOUND
We designed and implemented a prototype tutorial system for language learning that leverages a semantics centered approach for the analysis and correction of errors produced by language learners. The system uses a computational grammar augmented with rules for analysis, error diagnosis, and semantics centered generation of corrected forms.The system has been presented to both academic and industrial audiences. Further work would develop this initial prototype into a full end-to-end system relevant for commercial application.

LEARN MORE
Stanford Center for the Study of Language and Information

PEOPLE BEHIND THE PROJECT
Thomas Wasow is the Clarence Irving Lewis Professor of Philosophy, Emeritus and a Professor of Linguistics, Emeritus, at Stanford University. His interests include language processing, syntactic theory and linguistic methodology. He is the co founder of the Center for the Study of Language and Information (CSLI).

Emily Bender is Professor in the Department of Linguistics, Adjunct Professor in the Department of Computer Science and Engineering, faculty director of the CLMS program, and director of the Computational Linguistics Laboratory at the University of Washington. Dr. Bender has held positions at Stanford University and UC Berkeley, and worked in industry at YY Technologies. Dr. Bender received a PhD from the Linguistics Department at Stanford University in 2000.

Stephan Oepen is Professor in Computational Linguistics at the University of Oslo, where he heads the Division for Language Technology at the University of Oslo. Since 2000, he has also been a Senior Researcher at the Center for the Study of Language and Information, Stanford University. Stephan Oepen studied Linguistics, German and Russian Philology, Computer Science, and Computational Linguistics at Berlin, Volgograd, and Saarbrücken.

Dan Flickinger is Senior Research Associate at the Center for the Study of Language and Information (CSLI) and Project Manager of the LinGo Laboratory.