NLP for Sinhala & Tamil | Sri AI

Course overview

Both languages are low-resource, morphologically rich and written in their own scripts. This is the course that exists nowhere else, and the reason the Academy was founded.

Level: Advanced  ·  Mode: Full-time or part-time

Who this course is for

Engineers and linguists who want to build language technology for languages the global labs ignore.

What you will learn

• Build tokenisers that respect Sinhala and Tamil morphology
• Assemble and clean a corpus from scratch
• Fine-tune multilingual models on low-resource languages
• Evaluate honestly when no benchmark exists for your language

Syllabus

1. Module 1: Scripts, Unicode and normalisation
2. Module 2: Morphological analysis
3. Module 3: Corpus construction and cleaning
4. Module 4: Transfer learning from high-resource languages
5. Module 5: Building your own evaluation set
6. Module 6: Code-switching and how Sri Lankans actually write

Final project

Every module ends in hands-on practice, and the course ends with a project you build and present. Your certificate names that project.

Before you start

Python for AI, or equivalent experience.