NLU-11: Week 7 | Open Course Materials

This week, we will look at ethics in NLP and at the application of question answering.

Lab 3 takes place this week. Please have a look at the lab exercises before you attend the lab session, especially at Section 1:

Lab 3: Tensor Computation in PyTorch

This lab teaches tensor computation, batchification and masking in PyTorch. These are all things that you will need for coursework 2, so please make sure that you attend your lab session, it is likely to be a big help with your coursework.

Coursework 2 has been issued and is due on Friday 22 March at 12:00. Please bear in mind that some aspects of the coursework will be time consuming to run. Start working on the coursework early! The question sheet contains more guidance on this, please read it now.

Here are the solutions for last weeks tutorial:

Solutions for Tutorial 3

Slides	Lecture	Course Content
Ethics in NLP [handout]	19 (Birch)	Required reading: The Social Impact of Natural Language Processing, Hovy and Spruit (2016) Additional reading (not examinable): Ethical and social risks of harm from Language Models Weidinger et al. (2021) An Introduction to Data Ethics, Vallor and Rewak. A Framework for Understanding Unintended Consequences of Machine Learning, Suresh and Guttag (2019)
Bias in Word Embeddings [handout]	20 (Birch)	Required reading: Semantics derived automatically from language corpora contain human-like biases, Caliskan et al. 2017 Additional reading (not examinable): Process for Adapting Language Models to Society (PALMS) with Values-Targeted Datasets Irene Solaiman, Christy Dennison 2021
LLMs, Alignment, and Evaluation (Instruction Fine-Tuning & RLHF)	21 (Minervini)	Required Reading: - Language Models are Few-Shots Learners: https://arxiv.org/abs/2005.14165 - Super-Natural Instructions: Generalization via Declarative Instructions on 1600+ Tasks: https://arxiv.org/abs/2204.07705 Optional Reading: - Improving Language Understanding by Generative Pre-Training: https://cdn.openai.com/research-covers/language-unsupervised/language_understanding_paper.pdf - See the references in the slides :)

Files

qa.pdf (4.08 MB)

evalv2.pdf (5.65 MB)

License