LEGAL STUDIES 190, FALL 2022
Natural Language Processing & Law
Instructor: Ilya Akdemir
The goal of this course is to examine natural language processing tools and techniques and how they can be used with legal text data.
| Module | Summary | Berkeley Datahub Link |
|---|---|---|
| Notebook 1 | Introduction to Anaconda |  |
| Notebook 2 | Introduction to Python, Jupyter Notebooks, Pandas and Visualizations | |
| Notebook 3 | Introduction to case.law API | |
| Notebook 4 | N-Grams, Preprocessing, Tokenization, and non-Machine Learning Approaches to Text | |
| Notebook 5 | Supervized Machine Learning - Text Classification | |
| Notebook 6 | Unsupervised Machine Learning - Topic Modeling and Clustering | |
| Notebook 7 | Word Embeddings - Word2Vec and Doc2Vec | |
| Notebook 8 | Contextualized Word Embeddings - NLP with Transformers | |
Developer Team Lead: Arushi Sharma
Developer Team: Eddie Guo, Ukiah Heasley, Charlie Cheng-Jie Ji, Parth Shisode
These notebooks borrow code from multiple sources:
- Spring 2022 UC Berkeley, Legal Studies 123 "Law, Data and Prediction", instructed by Jonathan Marshall - https://github.com/ds-modules/Legalst-123
- Spring 2022 ETH Course, "Natural Language Processing for Law and Social Science", instructed by Elliott Ash - https://github.com/elliottash/nlp_lss_2022
- case.law API example notebooks - https://github.com/harvard-lil/cap-examples
- Jupyter notebooks for the "Natural Language Processing with Transformers" book (2022) - https://github.com/nlp-with-transformers/notebooks