• Skip to main content
  • Skip to secondary menu
  • Skip to primary sidebar

FromThePage Blog

Crowdsourcing, transcription and indexing for libraries and archives

  • Home
  • Interviews
  • crowdsourcing
  • how-to
  • Back to FromThePage
  • Collections

10 Ways AI Will Change Archives

January 10, 2024 by Sara Brumfield

We recently hosted a webinar entitled "10 Ways AI Will Change Archives," and today, we're sharing the insights from that presentation with you. AI is a transformative force, and often scary. Today, though, we’re sharing specific examples of using AI for good – allowing more people to find and interact with archival resources. 

1. Improving Accessibility

In the webinar, we discussed how AI can enhance accessibility within archives. We shared an example of a letter hosted on the Folger Shakespeare Library's EMMO platform and discussed the challenges of making historical documents accessible to modern readers. AI, particularly Large Language Models like ChatGPT, showed promise in regularizing diplomatic transcriptions, making them more accessible to all. AI also aids in improving the experience for visually impaired individuals and enables efficient full-text searches.

2. Extracting Entities

Next, we explored how AI can be used to extract entities from historical texts. We conducted experiments on a Virginia tobacco farm diary, demonstrating ChatGPT's ability to identify people and places mentioned in the text. This technology can be a valuable tool for researchers, historians, and archivists.

3. Matching Entities

We delved into the process of matching entities in texts to an authority file or finding aid, using the same farm diary as an example. AI showed impressive results, even handling cases of ambiguity, and proved to be a valuable tool in improving entity matching in archival materials.

4. Describing Items

We discussed experiments Matt Miller conducted using AI to summarize letters from the Library of Congress’s Susan B. Anthony collection. The ability to generate summaries, whether single-sentence or more extensive, has the potential to aid researchers in quickly understanding the content of documents.

5. Improving Discovery

AI can enhance discovery in archives by offering semantic search capabilities. We explored a case from the Susan B. Anthony papers, highlighting the ability to find conceptually similar texts and discover hidden connections within large collections.

6. Conversational Discovery Interfaces

Imagine interacting with archival collections in conversational language. We presented an experiment where an AI bot retrieves relevant information from collections based on user questions, providing attribution and references.

7. Creating Text from Handwriting

One of the challenges in archives is handling handwritten documents. AI has advanced significantly in handwritten text recognition, offering opportunities to make these materials more accessible and searchable.

8. Enhancing "Dirty" Text

We explored the potential of using AI to improve text quality, particularly in cases where automated transcription may produce errors. While AI corrections showed promise, there are challenges in dealing with poorly transcribed text, as the quality of corrections depends on the quality of the original text. We emphasized that AI should complement, not replace, human expertise in this context.

9. Transcribing A/V

AI can also play a crucial role in transcribing audiovisual materials, making them more accessible and discoverable. We shared examples of AI-assisted transcription using WhisperAI, demonstrating its potential to save time and resources compared to traditional transcription methods.

10. Changing Archival Workflows

Finally, we discussed how AI can reshape archival workflows, from digitization to access and preservation. With the wealth of data AI can generate, we'll need to rethink our systems and processes to harness its full potential.

We are excited about the future of archives and the potential AI holds for preserving and sharing our rich historical heritage. We are excited about the possibilities it brings and look forward to exploring these avenues further with you. One thing we know – text transcription and public engagement will both be a key part of these projects.  Want to explore these ideas more?  We love to have conversations with folks about these ideas – please reach out.  

Thank you for your interest in our work and the world of archives.

Want more? Here’s the recording of the webinar.

Filed Under: Uncategorized Tagged With: newsletter

Primary Sidebar

What’s Trending on The FromThePage Blog

  • Guide to Digitizing Your Archives
  • How to Handle Racial or Ethnic Slurs &…
  • 10 Ways AI Will Change Archives
  • How LLMs Work & A Handwritten Text Recognition Sandbox
  • Spreadsheet Transcription in FromThePage
  • Transcriptions, Screen Readers, and ChatGPT

Recent Client Interviews

An Interview with Candice Cloud of Stephen F. Austin State University

An Interview with Shanna Raines of the Greenville County Library System

An Interview with Jodi Hoover of Digital Maryland

An Interview with Michael Lapides of the New Bedford Whaling Museum

An Interview with NC State University Libraries

Read More

ai artificial intelligence crowdsourcing features fromthepage projects handwriting history iiif indexing Indianapolis Indianapolis Children's Museum interview Jennifer Noffze machine learning metadata newsletter ocr paleography podcast racism Ryan White spreadsheet transcription transcription transcription software

Copyright © 2025 · Magazine Pro on Genesis Framework · WordPress · Log in

Want more content like this?  We publish a newsletter with interesting thought pieces on transcripion and AI for archives once a month.


By signing up, you agree to our Privacy Policy and Terms of Service. We may send you occasional newsletters and promotional emails about our products and services. You can opt-out at any time.  We never sell your information.