Unlocking The Colonial Archive

Welcome

The UCA Project

The Spanish empire controlled the majority of the Western Hemisphere’s lands and peoples for more than three centuries. Its vast administration in the Americas depended on the work of royal notaries, Indigenous artists, and printers, who produced prodigious amounts of written and printed documents. Despite the extensive documentation, present-day understanding of the Spanish colonial enterprise is fragmentary due to the archive’s intellectual inaccessibility: Scholars and interested audiences must decipher archaic penmanship, obscure writing conventions, and unfamiliar Indigenous imagery to read these historical sources—a task that requires trained eyes. This project seeks to use artificial intelligence (AI) technologies to automatically convert this “unreadable” archive into accessible data.
We seek to develop interdisciplinary data science methods for the study of early-modern Indigenous- and Spanish-language materials—sources that have been mostly neglected in the computer science field. We propose three main research areas to (1) expedite the transcription of Spanish American documents using handwritten text recognition (HTR) technology, (2) automate the identification and linking of information within this corpora using natural language processing techniques and linked open data models, and (3) facilitate the automated search and analysis of pictorial elements in the Spanish colonial archive through computer vision approaches. Our aim is to design and test three reproducible workflows along these axes, combining machine learning, an AI approach, with the close reading of textual and pictorial materials. Our goal is to revolutionize how cultural institutions provide access to their collections, and how humanities researchers can undertake cutting-edge digital scholarship in the study of colonial Latin America.