Language Models

Learning Outcomes

Language Models (LMs) are a core component of Natural Language Processing (NLP), enabling systems to understand and generate text. This course focuses on both statistical language models (such as n-grams) and more recent transformer-based architectures (including the BERT and GPT families). By the end of the course, students will be able to use and adapt language models for tasks such as sentiment analysis and text classification, and will also understand how these models work at a fundamental level.

In particular, students will be able to:

a) Identify the main components of a language model;

b) Understand how language models are trained;

c) Adapt language models to new tasks;

d) Critically evaluate the opportunities, risks, and ethical considerations associated with language models.