Computer Assisted Language Learning

Abstract
We are developing a dialogue system for English conversation tutoring. It aims to provide intelligent one-to-one English conversation tutoring instead of old fashioned language education with static multimedia materials. This system can understand poor expressions of students and it enables green hands to engage in a dialogue in spite of their poor linguistic ability, which gives students interesting motivation to learn a foreign language. And this system also has educational functionalities to improve the linguistic ability. To achieve these goals, we have developed a statistical natural language understanding module for understanding poor expressions and an example-based dialogue manager with high domain scalability and several effective tutoring methods.
- Language understanding for the non-native
- Improve robustness by adopting statistical methods
- Use features designed for common errors of non-native speakers
- Flexible dialouge modeling for diverse conversation themes
- Improve scalibility by adopting data driven methods
- Example-based dialogue management can support various domains easily
- Tutoring methods and Feedback generation
- Implicit tutoring helps students learn appropriate expressions without stress
- Explicit tutoring helps students continue the conversation when they do not know what to say
- Final feedback indicate week points of an individual student
Research Issues
System Architecture

- Even though the expressions of students are not perfect, the system can provides sound examples on screen
Implicit Tutoring

- When students do not know what to say, the system provides explicit tutoring so that students can continue the conversation
Explicit Tutoring

- Assessment
- Collect assessment data for learning session and calculate final score to give feedback
- Feedback message reflects individual perspective to improve
- Criteria
- Mission Completion
- Elapsed Time
- Utterance Suitability
- Help Frequency
- Filler Word Frequency
- Contact

Research Page | Top | Home San 31, Hyoja-Dong, Pohang, 790-784, Korea
Phone: +82 54 279 5581 | Fax: +82 54 279 2299
Feedback generation