8 panels · 46 talks
Lightning Talks
Short, focused presentations grouped by theme. Each panel brings together 5–6 rapid-fire talks that trace a single thread — from minority scripts to community-led transcription.
Panels
- i.
Scripts of the World
Building Text Recognition Models for Diverse Languages and Writing Systems
All six talks show what happens when language or script sits outside the European mainstream — methodologically, linguistically, technically.
5 talks
- ii.
From Records to Rows
Structuring Serial Sources and Genealogical Data for Databases
Structured mass sources, demographic and legal serial records, and end-to-end workflows from HTR to usable data.
5 talks
- iii.
Scaling the Pipeline
API Integration, Large-Scale Workflows, and Benchmarking
What comes after transcription? All six talks present concrete pipelines leading from HTR output to structured, reusable data.
6 talks
- iv.
Mastering Complexity
Advanced Segmentation and Text Recognition for Challenging Documents
All six talks wrestle with material that actively resists standard HTR — physically, structurally, or linguistically.
6 talks
- v.
Archival Transformations
Bridging the Gap between Hidden Records and Public Access
Geographic and institutional diversity from Peru to Malta, from diocesan archives to fiction writing.
6 talks
- vi.
The Human Element
Collaborative Ecosystems in HTR and Research
HTR as a communal practice — institutional, citizen-driven, and international.
6 talks
- vii.
Teaching Machines, Teaching Humans
HTR Literacy, Ethics, and Creative Practice
HTR as a pedagogical tool — in university classrooms, secondary schools, and professional training settings.
6 talks
- viii.
Beyond the Transcription
Named Entity Recognition, Semantic Enrichment, and Digital Editing
When is general-purpose AI sufficient, and when is specialisation required? A direct answer to the conference theme "Not All AI Is Created Equal".
6 talks