Unlocking the Colonial Archive: Harnessing Artificial Intelligence for Indigenous and Spanish American Historical Collections

FAIN: HC-278116-21

University of Texas, Austin (Austin, TX 78712-0100)
Kelly McDonough (Project Director: August 2020 to present)

The transformation of Indigenous and Spanish colonial archives into readable and accessible data using artificial intelligence technologies, including transcribed texts, linked information, and automated search and analysis of pictorial elements. The UK partner, Lancaster University, is requesting £199,910 from the Arts and Humanities Research Council.

This project seeks to transform unreadable Indigenous and Spanish colonial archives into accessible data using artificial intelligence technologies. The core project team will consist of interdisciplinary researchers from LLILAS Benson Latin American Studies and Collections at the University of Texas at Austin, the Digital Humanities Hub at Lancaster University, and Liverpool John Moores University. We propose three main research areas to (1) expedite the transcription of Spanish American documents using handwritten text recognition 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. The research will be based on three digital collections under the aegis of LLILAS Benson and one from the National Archive of Mexico.

Associated Products

NEH-AHRC Paleography and Digital Humanities Fall 2021 Institute (Conference/Institute/Seminar)
Title: NEH-AHRC Paleography and Digital Humanities Fall 2021 Institute
Author: Palacios, Albert A.
Author: Perez Zamarripa, Abisai
Abstract: The online institute provided participants with practical training in the reading and visualization of 16th- to 18th-century manuscripts in Spanish. The objectives were twofold: First, they learned and honed paleography skills for the accurate reading and transcription of these materials through group transcription sessions and homework. Second, they obtained specialized training on several free and open source tools that can be used to facilitate collaborative research and visualize data in colonial texts. The goal was to cultivate a community of practice, support, and exchange for researchers studying the Spanish Empire that continues beyond this institute.
Date Range: November 1-December 17, 2021
Location: Online
Primary URL: https://docs.google.com/document/d/1N71m_jCG4hi-Y3Xm9A77JW0ZV_8SNwSs2-ZxfMRfYU8/edit?usp=sharing
Primary URL Description: URL of the institute program in Google Docs.

NEH-AHRC Paleography and Digital Humanities Spring 2022 Institute (Conference/Institute/Seminar)
Title: NEH-AHRC Paleography and Digital Humanities Spring 2022 Institute
Author: Palacios, Albert A.
Author: Perez Zamarripa, Abisai
Abstract: The online institute provided participants with practical training in the reading and visualization of 16th- to 18th-century manuscripts in Spanish. The objectives were twofold: First, they learned and honed paleography skills for the accurate reading and transcription of these materials through group transcription sessions and homework. Second, they obtained specialized training on several free and open source tools that can be used to facilitate collaborative research and visualize data in colonial texts. The goal was to cultivate a community of practice, support, and exchange for researchers studying the Spanish Empire that continues beyond this institute.
Date Range: January 24-March 11, 2022
Location: Online
Primary URL: https://docs.google.com/document/d/1HcZJFDepB_919ckCPLAucPaifINwX7JbQdXR9utfRck/edit?usp=sharing
Primary URL Description: URL of the institute program in Google Docs.

Leveraging Collaborative Scholarship and Handwritten Text Recognition Technology to “Read” the Spanish Colonial Archive (Public Lecture or Presentation)
Title: Leveraging Collaborative Scholarship and Handwritten Text Recognition Technology to “Read” the Spanish Colonial Archive
Abstract: Presentation on grant project objectives, approaches, and advances hosted by the Society of American Archivists--Latin American and Caribbean Cultural Heritage Archives Section. Presentation was part of the section's Desmantelando Fronteras/Breaking Down Borders Webinar.
Author: Palacios, Albert A.
Date: 07/30/2021
Location: Online
Primary URL: https://www.facebook.com/events/516635536213607/?active_tab=discussion
Primary URL Description: URL to Facebook event.
Secondary URL: https://connect.archivists.org/HigherLogic/System/DownloadDocumentFile.ashx?DocumentFileKey=64bbe940-08d1-4cf8-bfc9-905ff3290693
Secondary URL Description: URL to flyer.

Old Sources, New Technologies (Public Lecture or Presentation)
Title: Old Sources, New Technologies
Abstract: Presented on current NEH project and a previous project sponsored by the Transatlantic Platform for the Humanities and Social Sciences (T-AP) called "Digging into Early Colonial Mexico: a large-scale computational analysis of historical documents". The presentation was part of the LLILAS Benson "Digital Scholarship in the Americas" Speaker Series.
Author: Murrieta-Flores, Patricia
Date: 04/12/2021
Location: Online
Primary URL: https://www.youtube.com/watch?v=J119yPUGgsA
Primary URL Description: URL to recorded presentation in YouTube.

Data repository for transcriptions (Database/Archive/Digital Edition)
Title: Data repository for transcriptions
Author: Perez Zamarripa, Abisai
Author: Palacios, Albert A.
Abstract: Open access data repository for transcriptions produced under the grant. Transcriptions are available in txt files in various versions to facilitate reusability. The repository is organized by collection name. Transcriptions created under this grant are of materials in various archives in the Benson Latin American Collection.
Year: 2021
Primary URL: https://dataverse.tdl.org/dataverse/blac
Primary URL Description: URL to repository where we are depositing transcriptions created under the grant.
Access Model: Open access

Project presentation (Public Lecture or Presentation)
Title: Project presentation
Abstract: Presentation on the grant project and other LLILAS Benson digital scholarship initiatives given to members of the Texas Library Association's Innovation & Technology Round Table.
Author: Palacios, Albert A.
Date: 05-27-2021
Location: Online

Leveraging Handwritten Text Recognition Technology to “Read” the Spanish Colonial Archive (Conference Paper/Presentation)
Title: Leveraging Handwritten Text Recognition Technology to “Read” the Spanish Colonial Archive
Author: Palacios, Albert A.
Abstract: Presentation was part of a panel titled, "New Digital Methodologies in the Study of the Colonial World", given during the Latin American Studies Association conference. The presentation discussed ongoing work to transform the “unreadable” Spanish colonial archive into an accessible one using Transkribus, a platform that uses Handwritten Text Recognition (HTR) technology to automate the transcription of manuscript documents. Currently, the tool publicly provides pre-trained HTR models for 18th and 19th-century variants of English, Dutch, German, and French, but no models in 16th and 17th-century Spanish. Addressing this significant gap, the LLILAS Benson Digital Scholarship Office is training HTR models on four common early-modern Spanish calligraphic styles: escritura procesal, humanística cursiva, procesal-cortesana, and procesal-encadenada. Our goals are trifold: we hope to expedite the transcription of our digitized holdings of Spanish colonial materials, address the linguistic gap in HTR technologies, and share out the workflows and models we create to the broader scholarly and archival community.
Date: 05-28-2021
Conference Name: Latin American Studies Association

Fondo Real de Cholula (Conference Paper/Presentation)
Title: Fondo Real de Cholula
Author: Gómez García, Lidia E.
Author: Palacios, Albert A.
Abstract: Presentation on the collaborative transcription of the Fondo Real de Cholula, a digital collection under the auspices of LLILAS Benson. While the focus was on the digitization and teaching collaborations that have resulted from the University of Texas at Austin and the Meritorious Autonomous University of Puebla, the presentation included a brief overview of the grant project.
Date: 11-04-2021
Primary URL: https://www.historicas.unam.mx/eventos/2021/coloquio_humanidades_digitales_lenguas_indigenas.html
Primary URL Description: URL to conference program.
Conference Name: “Humanidades digitales y textos alfabéticos en lenguas indígenas”

"Inclusion in the Digital Humanities" (Public Lecture or Presentation)
Title: "Inclusion in the Digital Humanities"
Abstract: Presentation primarily focused on methods LLILAS Benson is deploying to broaden the inclusion of multilingual scholars in the creation and description of digital archives and projects. There was a brief overview of the grant project given towards the end. Presentation was part of the National University of Tres de Febrero (Argentina) "What Will Come: Digital Humanities" series.
Author: Palacios, Albert A.
Date: 09-14-2021
Location: Online
Primary URL: https://www.youtube.com/watch?v=tbxrfOMzRb8
Primary URL Description: URL of recording in YouTube.

‘Sobre el desarrollo de técnicas computacionales para el estudio de documentos históricos del México colonial’ (Public Lecture or Presentation)
Title: ‘Sobre el desarrollo de técnicas computacionales para el estudio de documentos históricos del México colonial’
Abstract: Keynote presentation for the "5to Coloquio de Investigación en Gestión Cultural" at the Universidad de La Ciénega del Estado de Michoacán de Ocampo.
Author: Murrieta-Flores, Patricia
Date: 06-25-2021
Location: Online

‘La decolonización de lo imaginario: Hacia la inclusividad y la consideración de lo subalterno en las Humanidades Digitales’ (Public Lecture or Presentation)
Title: ‘La decolonización de lo imaginario: Hacia la inclusividad y la consideración de lo subalterno en las Humanidades Digitales’
Abstract: Keynote for the "V Congreso de Humanidades Digitales Hispánicas"
Author: Murrieta-Flores, Patricia
Date: 10-04-2021
Location: Santiago de Compostela, Spain

‘La aplicación de Inteligencia Artificial para el estudio de documentos históricos del México colonial temprano’ (Public Lecture or Presentation)
Title: ‘La aplicación de Inteligencia Artificial para el estudio de documentos históricos del México colonial temprano’
Abstract: Keynote for the "IV Congreso Internacional de Humanidades, Universidad Autónoma de Monterrey"
Author: Murrieta-Flores, Patricia
Date: 05-19-2021
Location: Online

Los retos de la aplicación de técnicas de Inteligencia Artificial en Historia (Public Lecture or Presentation)
Title: Los retos de la aplicación de técnicas de Inteligencia Artificial en Historia
Abstract: Presentation given at the "XLI Congreso Nacional y XXVI Internacional de Geografía, Valparaiso, Chile"
Author: Murrieta-Flores, Patricia
Date: 10-01-2021
Location: Valparaiso, Chile

Inteligencia Artificial e Historia: La utilización de técnicas computacionales para la extracción de información y análisis de documentos históricos (Conference Paper/Presentation)
Title: Inteligencia Artificial e Historia: La utilización de técnicas computacionales para la extracción de información y análisis de documentos históricos
Author: Murrieta-Flores, Patricia
Abstract: -
Date: 01/19/2021

---