Natural Language Processing
Graduate level, University of Pennsylvania, 2025
Useful links:
- Course website: https://www.cis.upenn.edu/~myatskar/teaching/cis5300_fa25.
Overview
This course provides an introductory overview of the field of natural language processing. The goal of the field is to build technologies that will allow machines to understand human languages. Applications include machine translation, automatic summarization, question answering systems, and dialog systems.
The course material is based on two textbooks:
- Speech and Language Processing, 3rd edition draft, by Dan Jurafsky and James H. Martin.
- Natural Language Processing by Jacob Eisenstein.
Schedule:
| Week | Topics |
|---|---|
| 1 | Introduction |
| 2 | Sentiment analysis and naive Bayes |
| 3 | Logistic regression, perception and N-gram language models |
| 4 | Vector space models and neural vector space models |
| 5 | Neural networks |
| 6 | Recurrent neural nets, sequence to sequence, and attention |
| 7 | Transformer |
| 8 | Contextualized embeddings |
| 9 | NLP datasets and applications, machine translation |
| 10 | Large language models |
| 11 | Efficient language models |
| 12 | Interpretability |
| 13 | Dataset biases |
| 14 | PhD research spotlight |
| 15 | Wrap-up |