University Libraries to expand digital access and discovery of hidden knowledge
Credit: Virginia Tech
The University Libraries was recently awarded two grants totaling almost $600,000 from the U.S. Institute of Museum and Library Services’ (IMLS) National Leadership Grants program. This program funds and supports projects that strengthen the quality of library and archive services across the nation by advancing theory and practice.
Only two Virginia awards were given this year from this program and both were awarded to the University Libraries at Virginia Tech. These grants total one of the largest awards in this cycle from IMLS.
“It is rare to be granted more than one grant in the same year, and we are very honored,” said Tyler Walters, dean of the University Libraries. “This shows that the work being done by our faculty is on the leading edge of this discipline.”
During the past five years, the University Libraries has been one of the most funded academic libraries in the nation by IMLS and is making a significant contribution through national-level digital infrastructure initiatives.
Sens. Mark R. Warner and Tim Kaine stated in their recent press release that “Academic libraries are an invaluable resource with the potential to benefit universities and communities across the commonwealth,” said the release. “We are thrilled that this grant will allow Virginia Tech and the Blacksburg community to activate a wealth of existing knowledge and continue to foster learning and innovation.”
Of the two grants, $505,214 will be awarded to the project: Opening Books and the National Corpus of Graduate Research, led by Assistant Dean Bill Ingram, in collaboration with Edward A. Fox from the Virginia Tech Department of Computer Science and Jian Wu from Old Dominion University Department of Computer Science.
The project’s goal is to deploy natural language processing, machine learning technologies to advance discovery, use, and reuse of knowledge hidden in the text of books and other book-length documents. The research will focus on bringing computational access to book-length documents, such as large national corpus of freely available electronic theses and dissertations (ETDs), free from the legal restrictions generally imposed by book publishers. The team will create methods for extracting and analyzing segments of long documents and put systems in place for summarizing chapters of longer texts and making it easier for users to find the information they need.
A wide range of audiences can benefit from this research, including librarians, students, authors, educators, and researchers.
Virginia Tech has been a world leader in ETD initiatives for over 20 years. Theses and dissertations have been published at Virginia Tech since 1903, and in 1997 it was the first university to require electronic submission of theses and dissertations. Today, many universities require students to submit a copy of their thesis to an institutional digital repository that then makes the dissertation freely available online.
“As a librarian and a computer scientist, I see the enormous, transformative potential of machine learning to computationally process library collections, leverage them to advance research and education, and increase their use,” said Ingram. “This will allow libraries to provide a greater impact for our users.”
For the second grant, $87,151 will be awarded to Community Development Model for Digital Community Archives, led by Nathan Hall, director of digital imaging and preservation services. This project is in collaboration with Protect Our Water, Heritage, Rights Coalition (POWHR), and Ralph Lutts of Blue Ridge Heritage.
“What’s novel here is that we are laying the groundwork to create a community-led digital archive,” said Hall. “We are collaborating with cultural heritage organizations and with regional groups focused on coal and gas industries and their effects on the natural environment, human health, and labor.”
This project expands digital access to regional collections and networks that are rich in cultural heritage but are isolated due to the absence of robust digital infrastructures. As a result of this project, communities will have greater digital access to geographically, socially, and politically siloed collections and networks.
“This project is going to connect community organizations in rural Virginia, and enable more people to become aware of their missions,” said Hall. “We hope to demonstrate a different way of developing archival collections and a new kind of partnership between academic libraries and communities.”
Without preservation, cultural heritage could be forgotten over time. This project aims to prevent that from happening. “We’ll be bringing different narratives together to show how they are connected, and how these connections can be avenues for mutual support and benefit between these organizations, with the University Libraries as a supporting resource,” said Hall.
Although this project is in the preliminary stages, Hall hopes that in the future this grant could be the starting point that leads to developing and advancing open access collections, which could give others the ability to access and learn of their heritage or research a culture.