NLU-11: Week 9 | Open Course Materials

This week, we we will have the first lecture on movie summarisation and the next two lectures on summarisation and parameter efficient fine tuning.

As a reminder, Coursework 2 has been issued and is due on Friday 22 March at 12:00 noon.

This week's lab is on prompting with GPT-3.5. It even includes a small competition on who can develop the best performing prompt on a small data set! Please note you will need an OpenAI key to run this lab; please obtain this before you attend your lab session, instructions can be found in the lab itself.

Lab 4: Prompting with GPT-3.5

The solutions for last week's tutorial are now available:

Solutions for Tutorial 3

And here is a preview of next week's tutorial. Please work through this before attending your tutorial group next week:

Tutorial 4: Summarization

Slides	Lecture	Course Content
Movie Summarisation	25 (Keller)	Guest lecture - not examinable Required reading: none Additional reading: Movie Summarization via Sparse Graph Construction. Papalampidi, Keller, Lapata, 2021.
Summarisation	26 (Minervini)	Required reading: - Don't Give Me the Details, Just the Summary! Topic-Aware Convolutional Neural Networks for Extreme Summarization - A Thorough Examination of the CNN/Daily Mail Reading Comprehension Task
Parameter-Efficient Fine-Tuning	27 (Minervini)	Required reading: - Parameter-Efficient Fine-Tuning Methods for Pretrained Language Models: A Critical Review and Assessment - LoRA: Low-Rank Adaptation of Large Language Models

Files

summarisation.pdf (4.08 MB)

peft.pdf (1.65 MB)

License