Glite Get Started
Glite menu
Research

Research areas

Glite’s N+1 learning architecture

Glite’s N+1 architecture: the Concept Extractor identifies learning concepts. The Knowledge Predictor combines them with the student’s learning history. The Orchestrator uses knowledge estimates, the Knowledge Graph and the Activity Bank to choose the next concept and activity.
Open a component below for its explanation and related research.
Student

The learner answers questions and completes activities. Their responses provide evidence about what they know.

Learning history

A record of answers and learning activities. The models use this history to update estimates and choose the next task.

Learning materials

Books, videos and other content contain learning concepts. Identifying those concepts connects materials to a learner’s needs.

Concept Extractor

Identifies the learning concepts in content and student answers: word meanings, expressions, skills and misconceptions.

Learning concepts

The units the system recognises and teaches. For English, these include individual word meanings and expressions.

Knowledge Predictor

The Knowledge Prediction model combines concepts with a learner’s history to estimate what that learner already knows.

Knowledge probabilities

Estimates between zero and one express uncertainty about a learner’s knowledge of each concept. They can change as new evidence arrives.

Orchestrator / Virtual Tutor

Selects the next concept and activity using learning history, knowledge estimates and the available tasks.

Knowledge Graph

Organises the concepts that can be taught. Depending on the domain, it may include explicit relationships or a collection of concepts without them.

Next task

Pairs a learning concept with an activity. The learner’s response becomes part of the history for the next decision.

Activity Bank

The available learning activities: different ways to practise, explain or assess a concept.

Reinforcement learning in education

Teaching is a sequence of decisions. The next activity should depend on what a learner knows, what they need to learn and what earlier activities changed.

Knowledge tracing

A student’s answer is evidence about their knowledge. It is not a complete description of it.

Concept extraction

We give the concept extractor text, audio or video, and it identifies the learning concepts.

Knowledge graphs

A learning system needs an explicit account of the concepts it can teach.

Research methods

Research automation needs verifiable experiments and an inspectable record of what happened.