Applications of Large Language Models to the Humanities Workshop 21 Nov 2023

Applications of Large Language Models to the Humanities Workshop

In this workshop, we will explore different approaches for applying a Large Language Model (like BERT) to a specific tagging problem in the context of Computational Humanities research. Following up on the current “pre-train and fine-tune” paradigm in the field of Computational Linguistics, we will try to reach an understanding of the techniques used in the “fine-tuning” step. Besides this theoretical part, we will have a hands-on session on working with computing clusters. Because carrying out this type of approach requires computational power often not available in personal computers, we will walk through an example of how to script and deploy fine-tuning jobs on ALICE (the high performance computing cluster at Leiden University). We will complete the workshop emphasising the need for evaluation and comparison of different approaches before consuming the output of the fine-tuned models.

Instructor

Enrique Manjavacas Arevalo

Location

Location: Digital Lab, P.J. Veth 1.07

Date & Time

The workshop will take place on 21 Nov 2023, 10:00-13:00

Availability

This workshop is only available in person. Please register here