Linguistic Constructs as the Representation of the Domain Model in an Intelligent Language Tutoring System

TL;DR

This paper introduces Revita, an AI-powered language tutoring platform that uses a novel system of linguistic constructs to represent domain knowledge, supporting personalized feedback and progress evaluation for learners across multiple languages.

Contribution

It presents a new approach of using linguistic constructs as domain models in an intelligent language tutoring system, developed with expert collaboration.

Findings

System supports learners from low-intermediate to advanced levels.

Feedback and exercise content are tailored using linguistic constructs.

Pilot studies involve hundreds of students providing iterative development insights.

Abstract

This paper presents the development of an AI-based language learning platform Revita. It is a freely available intelligent online tutor, developed to support learners of multiple languages, from low-intermediate to advanced levels. It has been in pilot use by hundreds of students at several universities, whose feedback and needs are shaping the development. One of the main emerging features of Revita is the introduction of a system of linguistic constructs as the representation of domain knowledge. The system of constructs is developed in close collaboration with experts in language teaching. Constructs define the types of exercises, the content of the feedback, and enable the detailed modeling and evaluation of learning progress.