Words Into Data is part of a series of workshops for Love Data Week, an annual festival highlighting topics, opportunities and services relevant to data in research.

This interactive workshop will familiarize users with a basic natural language processing (NLP) research pipeline using the Huggingface/transformers framework. You will learn to ingest, process, and tokenize text; extract Named Entity (people, places, events, etc.) data from it; and reformat that data so it can be used in higher-order research workflows like mapping, social network analysis, and more. Time allowing, we might even make a map or network graph ourselves!

Register here to attend. Spots are open to current Stanford Affiliates only and will be offered on a first-come, first-serve basis. Space is limited, and a waitlist will be available once all spots are filled. (Please note: You must be logged in to Google Drive with your Stanford email, such as YourSUNetid@stanford.edu, to access the registration form.)
 

• Location: Virtual
• Date and Time: 2:00PM to 3:00PM PT on Monday, February 10, 2025
• Instructor: Brad Rittenhouse, Research Data Facilitator, Stanford Research Computing