Magical Meaning Machines: Practical explorations of Large Language Models for digital scholarship
Workshop hosted by the Centre for Digital Scholarship and the AI and ML Competency Centre
Join us at the Centre for Digital Scholarship, Weston Library, on Wednesday 20 November for this practical workshop which will explore opportunities for new kinds of digital scholarship in the humanities and social sciences presented by Large Language Models.
Led by Dominik Lukeš, Lead Business Technologist at the AI and ML Competency Centre, the workshop will present Large Language Models as a new kind of machine for processing semantic information in text with completely new capabilities and also new limitations. It will then explore what opportunities these new machines present for digital scholarship based on practical examples. These opportunities lie not only in using Large Language Models as tools to assist with text data but also as a new kind of object to study.
The workshop is focused on enabling scholars in the humanities to get started with using Large Language Models in their work - no prior experience or knowledge is required. It will combine brief explanations and case studies with hands-on activities.
Topics
The workshop will cover the following topics:
-
Capabilities and limitations of Large Language Models
-
Types of Large Language Models and differences between them
-
Tools to explore properties of Large Language Models
-
Architecture of applications built on Large Language Models
-
Key characteristics of Large Language Models of importance to the humanities
-
Uses of Large Language Models in scholarship in the humanities
Pre-requisites
No prior knowledge or experience required. However, participants should create free accounts with the following tools to facilitate hands-on activities and bring laptops.
- ChatGPT
- Claude.ai
- NotebookLM (requires free Google account)
- Google AI Studio (requires free Google account)
- Sketch Engine
Dominik Lukeš is a Lead Business Technologist at the AI and ML Competency Centre with a focus on digital scholarship and academic practice. Prior to joining the Centre he started the Reading and Writing Innovation Lab where he focused on technologies supporting reading and writing in academic contexts.
Dominik's background is in linguistics and translation. He has previously run workshops at Oxford on using corpus analysis tools for humanities research. Dominik’s core area of expertise is an intersection of conceptual metaphor theory and discourse analysis with a particular focus on construction grammar. He was the founding member of the journal Cognitive Approaches to Critical Discourse Analysis (CADAAD) and co-edited with Chris Hart the 2007 volume Cognitive Linguistics in Critical Discourse Analysis. He also translated George Lakoff's Women, Fire and Dangerous Things into Czech. He is the author of Czech Navigator, a grammar of Czech for non-native speakers.
He blogs on MetaphorHacker.net and maintains a site focusing on exploring Large Language Models as Semantic Machines and publishes an occasional newsletter on AI in Academic Practice.
