FNLP: Foundations of Natural Language Processing

Welcome to FNLP!

This course is normally taken by third year undergraduates.  It introduces you to basic concepts and techniques in Natural Language Processing and lays the foundations for more advanced NLP courses in year 4. We will focus on what makes automatic processing of language unique and challenging: its statistical properties, complex structure, and pervasive ambiguity. This course will cover a range of architectures and algorithms for NLP. We will start with simple models for text classification and generation. We will then discuss neural models to represent the meaning of words and model language, such as Recurrent Neural Networks and Transformers. You will gain insight into the technology behind contemporary Language Models, including pre-training, supervised fine-tuning techniques, and alignment. As part of the course, we will also introduce methodological and ethical considerations (e.g., evaluation, data collection, algorithmic bias) that are important for working in the field.   

Course Structure and Delivery

We will be delivering the course via three lectures a week, fortnightly tutorials in small groups,  and fortnightly labs (in person).  There will also be two assignments and non-assesed quizzes to  help check your understanding throughout the course. 

The course material for each week (including lecture slides, videos, required reading and quizzes) will appear on these pages (see right hand menu).  Visit the Learn page for the course for information about Assessment and your lab and tutorial groups (not yet assigned, check back in Week 1). 

The lectures will be delivered by Ivan Titov and Mirella Lapata (Ivan is course organiser). We very much look forward to teaching you all! 

Communication

When you sign up for the course, you will have access to:

• this website: the one place to find it all;
• the course mailing list: used for all essential communication;
• the Learn page of the course.

We will use Piazza forum for the course:

• you can use it to post questions about the course content, including tutorials, labs and assignment;
• the main purpose is peer support: students discuss course material and help each other;
• lecturers and TAs moderate the discussion and contribute;
• Piazza can be accessed through the link in Learn.