“`html

Joe Loewenstein, a lecturer in English and head of the Humanities Digital Workshop, both within Arts & Sciences, is set to act as co-principal investigator for a $798,000 Human Networks and Data Science grant provided by the National Science Foundation. Seth Kulick and Neville Ryant, both affiliated with the Linguistic Data Consortium at the University of Pennsylvania, will assume the roles of co-PIs.

The initiative, titled “TRACE: Enriching EarlyPrint,” expands upon the EarlyPrint Library, a digital compilation of 60,000 texts published in English from 1473 to the early 1700s, which Washington University in St. Louis manages in collaboration with Northwestern University. The funding will allow researchers to manually annotate selections from the EarlyPrint corpus, encompassing up to 1 million words; train advanced natural-language processing models on those annotated selections; and subsequently utilize those models to automatically annotate the complete EarlyPrint corpus of 1.65 billion words. After evaluating the resulting annotations, the team will reconstruct the EarlyPrint Lab, an affiliated platform that provides a variety of computational, analytical, and visualization tools for scholarly examination of this vast library.

The new annotation layers will cover various subjects, including word-sense clarification; syntactic assessment; and text co-referencing chains to related events and entities such as individuals, locations, and organizations. Upon completion, the annotated corpus will effectively serve as a comprehensive index of all individuals and occurrences that left their mark on 16th- and 17th-century English-speaking public discourse.

The WashU team will operate within the Humanities Digital Workshop of Arts & Sciences. Guided by Loewenstein’s colleagues Douglas Knox and Tumaini Ussiri, the annotators will comprise students from English, history, linguistics, statistics, and data science disciplines. WashU alumnus John Ladd (PhD ’19) will act as a consultant for the grant. Currently an assistant professor of computing and information studies at Washington and Jefferson College, Ladd has contributed to EarlyPrint since 2012, the year he joined WashU’s doctoral program in English.

Discover more about the project on the Humanities Digital Workshop website.

The article Loewenstein wins NSF digital infrastructure grant was first published on The Source.

“`