EAA – NLP Workshop using Python – 2023
Instructor: Ties de Kok (tdekok@uw.edu)        Location: virtual
Dates: March 29^th & April 12^th, 2023      Time: 9am – 11:15am (PST) /    6pm – 8:15pm (CET)

The recordings can be watched here.

Workshop description & objectives:

This workshop, titled “Modern approaches for processing textual data for research and teaching” will introduce participants to various techniques for programmatically processing textual data using Python. These techniques include basic approaches such as regular expressions and keyword counting, as well as modern machine learning approaches such as BERT and GPT models. The workshop will consist of two sessions.

For a teaser, see my blog post: “Beyond chat-bots: the power of prompt-based GPT models for downstream NLP tasks”

Workshop objectives:

By the end of this workshop, participants will be able to:

• Understand the various approaches available for processing textual data.
• Choose an appropriate NLP approach for their research project or classroom case.
• Find a starting point for implementing their chosen approach using Python.

Who is it for:

This workshop is designed for researchers and teachers who are already familiar with using Python for basic data analysis tasks, such as Pandas. It is not an introductory Python workshop, so participants should already have basic working experience with the Python programming language, Jupyter Notebooks/Labs/Google Colab, and the command line/terminal. This workshop is suitable for those looking to expand their Python skills, particularly about processing textual data for research or classroom purposes.

Prerequisites:

To participate in this workshop, you must have prior experience using Python for basic data analysis tasks, such as with Pandas. This includes familiarity with Python programming, Jupyter Notebooks / Google Colab, and the command line/terminal. Additionally, you will also need access to a computer with a stable internet connection. All necessary code and data will be provided by the instructor.

Important: to register for this course, you are required to solve a basic problem and submit your solution using the steps below:

• Start a Jupyter Notebook or Google Colab session.
• Import the Pandas library and read in a data file of your choice (e.g., csv/Excel/Stata).
• Create a visualization of your choice using the Matplotlib library, make sure the title of the plot reads “Data visualization for EAA – Python – 2023:”
• Save your solution to a notebook file (e.g., .ipynb)

You can register and submit your notebook file using the following form:

https://forms.gle/B1EjXPrwAZng6AAD7

Registration deadline: March 20^th 2023

Participants will be notified via email if they have been accepted into the workshop.