[Update, 11/4: this seminar has been cancelled due to sickness - sorry! A rescheduled/substitute talk from Prof. Thompson is upcoming on Nov. 18.]
Computational Humanities & Human-Centered Machine Learning
Laure Thompson, Assistant Professor, College of Information and Computer Sciences
CSSI Seminar, Fri 11/4 12:00-1:30pm, CS room 151
Machine learning (ML) is typically used to replicate some human activity. Given a set of inputs, a system is built to produce the same outputs as a human would; thus reducing human interaction through automation. In contrast to this standard use, the computational humanities typically use ML as a tool to enable human interaction in the form of human interpretation. This alternative use centers iterative, expert human use to study humanities collections in order to gain meaningful insights from and recognize the true complexities of cultural phenomena. In this talk, I will argue that these two uses are fundamentally different paradigms of user intention. I will illustrate the characteristics of these two paradigms using two case studies drawn from the computational humanities: a Dadaist "reading" of Dada and a largescale study of the themes in science fiction.
Laure Thompson is an assistant professor in the Manning College of Information & Computer Sciences at UMass Amherst, whose research bridges machine learning and natural language processing with humanistic scholarship. Centered on humanities applications, her research focuses on understanding what computational models actually learn and how we can intentionally change what they learn. Given this humanities focus, she works with a wide range of cultural heritage corpora: from texts of science fiction novels and medieval manuscripts to images of avant-garde journals and magical gems from the ancient Mediterranean. She completed her PhD in Computer Science at Cornell University in 2020.