The Course on Automated Exam Marking using AI it immerses you in the exciting world where the Artificial intelligence is transforming education. In a context where the digitalisation in education is booming; the ability to use AI to mark exams represents a a highly sought-after skill. This course offers you a in-depth understanding of the Fundamentals of AI-based assessment, approaching the issue from the basic principles up to the ethical challenges and the transparency. You’ll learn how to use the natural language processing (NLP) to improve the autocorrect and you will explore how the advanced language models, such as BERT y GPT, they can to revolutionise educational assessment. You’ll also delve into the design and development of automatic correction systems, understanding the workflow and the quality metrics. Taking part in this course puts you in a position to at the forefront of an educational revolution, opening doors to new career opportunities in a a constantly evolving labour market.
Automatic Exam Marking Using AI
AI Academy
3 pm
Introduction
Objectives
-
To know the principles of educational assessment and their current challenges.
-
Understanding the basic principles of AI applied to the assessment.
-
Identify types of automated assessment and its application in exams.
-
To analyse the ethics, the biases and the transparency in the AI-based assessment.
-
Understanding the role of the natural language processing (NLP) in the autocorrect exams.
-
Apply language models for to analyse written answers.
-
Design automatic correction systems with tools y metrics appropriate.
Table of Contents
TEACHING UNIT 1. FUNDAMENTALS OF AI-BASED ASSESSMENT
1. Educational assessment and its current challenges
2. Basic principles of artificial intelligence applied to assessment
3. Types of automated assessment: objective, formative and summative
4. Ethics, bias and transparency in AI-based assessment systems
5. Use cases in educational institutions and digital platforms
TEACHING UNIT 2. NATURAL LANGUAGE PROCESSING (NLP) FOR EXAMS
1. PLN and its role in automatic correction
2. Classification of responses: closed questions vs. open questions
3. Language models (BERT, GPT, etc.) applied to written responses
4. Semantic analysis techniques and the detection of incorrect answers
5. Limitations of PLN in automated assessment and how to mitigate them
TEACHING UNIT 3. DESIGN AND DEVELOPMENT OF AUTOMATIC CORRECTION SYSTEMS
1. Types of questions that can be marked automatically
2. Workflow: from collecting responses to providing feedback
3. Tools and platforms
4. Quality metrics
5. Integration with learning management systems