AI Agents for Sinitic Texts
Summer Workshop
This intensive four-day workshop will teach the latest applications of large language models (LLMs) to Sinitic texts, with a focus on agentic approaches—AI-driven workflows that can support and automate multi-step research tasks.
Overview
Organized by the Digital China Initiative (Principal Investigators: Peter Bol and Michael Szonyi).
The workshop will be led by Dr. Kwok-leong Tang, Managing Director of the Digital China Initiative, with a group of tutors. By the end of the workshop you will be able to use natural language to create programs to perform sophisticated research tasks at scale. The workshop will show how to bring AI to bear on all steps of the research cycle, from data collection and processing to analysis and presentation, using both qualitative and quantitative approaches. No prior digital humanities experience is required; participants without digital literacy are especially welcome.
Topics
Digitizing Materials
Digitizing non–digitally born materials
Data Collection
Collecting data online (web scraping; APIs)
Data Modeling
Turning unstructured data into structured data
Entity Extraction
Named entity extraction (people, places, dates, and other entities)
Knowledge Graphs
Networks and knowledge graphs
Custom Tools
Building custom digital tools for your research needs
Geospatial Analysis
LLM-assisted geospatial analysis
Schedule
Workshop Session 1
9:00 AM – 4:00 PM
Workshop Session 2
9:00 AM – 4:00 PM
Workshop Session 3
9:00 AM – 4:00 PM
Workshop Session 4
9:00 AM – 4:00 PM