Information extraction from heritage documents

Heritage documents contain a multitude of information such as names of people, places, dates, or events: how to identify and structure them to facilitate their indexing?

The theme of this first meeting is the automatic extraction of information using artificial intelligence in archives and documentary collections. Based on projects and case studies, we will examine techniques for extracting structured information from handwritten and printed documents.

At the heart of this session:

• Text recognition and information typing (OCR, HTR, NER) 

• Structuring extracted data and links to repositories 

• Evaluation of results and validation 

• Integration of data into search engines, link to source

The agenda

• 15 min for an overview of new developments (technology watch and public policies)
• 15 min for a focus on information extraction from projects and case studies 
• 15 min of questions and answers

For whom? Professionals from archives, museums, and heritage institutions involved in the description, documentation, research, or promotion of collections. 

On line — Duration : 45 min (in French)

TEKLIA AI Meetings 

TEKLIA offers you a series of five webinars dedicated to the uses of artificial intelligence in archives and museums. Each session combines a presentation of the latest technological developments, a thematic focus, and an exchange with participants.