Academic Author

Leveraging Large Language Models for Post-OCR Correction of Nineteenth-Century British Newspapers

by
Montage of images from this blog post, mixed with images from British Library Newspapers archive

│By Alan Thomas, AI Research Engineer at the Centre for Machine Intelligence, University of Sheffield│

Poor optical character recognition (OCR) quality is a major obstacle for humanities scholars seeking to make use of digitised primary sources such as historical newspapers. To improve the quality of noisily OCR’d historical documents, we introduce BLN600 – an open-access dataset derived from Gale’s British Library Newspapers – and showcase the potential of large language models (LLMs) for post-OCR correction using Llama.

Read more

Plans, Charts, Images and Drawings: Eighteenth Century Collections Online as a Source of Visual Information Transmission

by

│By Sirkku Ruokkeinen, University of Turku, Finland│

In 1786, the Scottish economist William Playfair (1759–1823) published the Commercial and Political Atlas, reporting on the trade balance between England and continental Europe, West Indies, and North America. The work included something never before seen in print: line and bar charts. These statistical tools, although familiar to many of us now, are in fact quite complex devices and necessitate some understanding of their structure for a successful reading. So how were Playfair’s eighteenth century readers able to understand them?

Read more

ECCO’ing through the Ages: Exploring Reception with Gale’s Eighteenth Century Collections Online

by
Reception Reader showing reuses of Shaftesbury’s A Letter Concerning Enthusiasm; overlaps with Astell’s An Enquiry After Wit highlighted by a red box.

│By David Rosson, Doctoral Researcher at the University of Helsinki│

A big-picture goal for the Computational History research group at the University of Helsinki is to develop methods for studying how ideas spread during the Age of Enlightenment. This was a time period marked by notable thinkers and burgeoning ideas about reason, science, human nature, the state, and society as a system operating on certain principles. These ideas have profoundly shaped the modern world we live in today and in many ways still bear influence on current affairs.

An indispensable resource for studying historical discourse in this period is Gale’s Eighteenth Century Collections Online (ECCO), which covers a considerable portion of books published in Britain between 1700 and 1800. Our research group has been working with the datasets and building research infrastructure on top of Gale’s primary sources for more than a decade. One of the latest examples of our researcher-oriented tools is a web interface, Reception Reader, that helps with the tasks of exploring text reuse patterns in ECCO documents.1

Read more