The Signature Talks program offers free training for your group through our most popular webinars, “Your First Crowdsourcing Project”, "10 Ways AI Will Change Archives and Libraries", and "Using HTR in People-Centered Transcription”, tailored to specific groups. This program is designed for groups of at least five people, providing a customized experience with a dedicated Q&A session to address their specific needs.
Signature Talks
Your First Crowdsourcing Project
Join Ben and Sara Brumfield of FromThePage as they step you through your first crowdsourcing project. The session covers selecting material, finding volunteers, developing transcription conventions, keeping volunteers engaged, and what to do with your transcriptions once you're done.
10 Ways AI Will Change Archives
AI is set to transform special collections and archives significantly. Through experiments and industry observations, we have identified ten ways AI will impact these institutions. This presentation highlights potential strategic implementations for university libraries.
First, we’ll explore how AI enhances accessibility by automating text regularization for better screen reader compatibility. We’ll then demonstrate AI's capabilities in extracting and matching entities within historical text.
Additionally, we’ll highlight AI's role in item description and discovery improvement, providing examples from the Library of Congress and FromThePage projects. The presentation will demonstrate AI-driven semantic search, which finds documents based on conceptual similarity rather than keywords and introduces an AI semantic search bot for conversational interaction with special collections.
We will address the application of AI in reading cursive handwriting, transcribing audio-visual materials, and transforming archival workflows. These advancements not only enhance researcher experience but also improve the efficiency of archival processes.
Finally, we will discuss the implications of AI-generated data on digital library frameworks, the challenges searching all of these derivatives will bring, and the need to track and manage this new data.
Join us to explore these advancements and their potential to redefine the future of digital libraries and archives.
Using HTR in People-Centered Transcription
How can artificial intelligence be used to support humans instead of replacing them?
This presentation demonstrates how we integrated Handwritten Text Recognition (HTR) into the FromThePage crowdsourcing platform while keeping the central role of humans in the transcription process.
We asked ourselves how can we introduce enough friction into our user interface that volunteers have to think rather than blindly trusting machine generated data, while still using AI to speed up their work and increase their pleasure? Our focus lay on enhancing user experience rather than on character error rates or model training.
We will discuss the state of the art in Handwritten Text Recognition (always changing!), design considerations, implementation specifics, and the initial outcomes of user testing conducted by the State Library of New South Wales and their Digital Volunteer working group.