Universiteit Leiden

nl en

Workshop

Applications of Large Language Models to the Humanities Workshop

Date
Tuesday 21 November 2023
Time
Explanation
Tuesday, 21 Nov 2023 at 10:00 – 13:00 (CET)
Location
Digital Lab in P.J. Veth 1.07
Room
Registration now closed.

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-tune models.

About Enrique: "I am currently a post-doc at the University of Leiden, working in the MacBERTh project developing Large Language Models for Historical Languages. I obtained my PhD at the University of Antwerp (2021) with a dissertation on computational approaches to text reuse detection."

 

Registration now closed.

Any questions contact: lucdh@hum.leidenuniv.nl.

P.J. Veth

This website uses cookies.  More information.