Background

Slides from the first lecture can be found here.

A cheat sheet on mathematical notation and a few basics for the class can be found here.

Additional materials

If you want to dig a bit deeper, here are a few (optional!) readings on the development trends of LLMs, a general textbook on NLP as well as a paper mentioned in the slides:

• Jurafsky & Martin (2024) Speech and Language Processing (textbook)

• Zhao et al. (2023) A survey of LLMs

• Kaplan et al. (2020) Scaling Laws for Neural Language Models

• Mikolov et al. (2013) Word2Vec paper