Natural Language Processing

Welcome to the Tufts Natural Language Processing course!

Natural Language Processing (NLP) is the study of human language with computational methods. In these modules, we will walk through the major skills of NLP, including but not limited to: text cleaning and processing, webscraping, and neural networks.

These materials were created by Peter Nadel, Digital Humanities Natural Language Processing Specialist between 2023 and 2025. For questions or corrections, please reach out to tts-research@tufts.edu.

01 Introduction

Introductory material for working with text in Python.

introduction/index.html

02 Text Processing

How to clean and begin to analyze large corpora including regex, TF-IDF and topic modelling.

text-proc/index.html

03 Webscraping

Explore data collection and curation.

webscraping/index.html

04 Using Pretrained Models

Wrap your head around common NLP tasks by using these pretrained models.

pretrained-models/index.html

05 Deep learning

Build models like BERT and GPT from scratch using Pytorch.

deep-learning/index.html

06 Large Language Models

Learn how to get the most out of both open-source and propritary large language models and artificial intelligence.

llms/index.html