Stephen Bothwell

Graduate Student

University of Notre Dame

Salve! My name is Stephen Bothwell, and I am a researcher whose interests are at the intersection of both the ancient and the modern. In particular, I study the application of techniques in natural language processing (NLP) to ancient languages. I am invested in unifying linguistic ideas and modern computational (e.g., neural) techniques.

Currently, I am a fourth-year graduate student in the NLP Group at the University of Notre Dame. I am advised by Dr. David Chiang, and I work on projects pertaining to linguistic attributes at a variety of granularities. One line of work concerns the derivation of phonological rules in historical linguistics, striving to add interpretability to derived systems of ancestor and descendant language forms through the determination of rules. Another line of work explores stylistics, attempting to pin down and capture the notion of rhetorical parallelism.

Aside from research, I also serve as a senior pedagogy fellow for the Navari Family Center for Digital Scholarship. I teach about neural networks, hoping to improve AI literacy. Thus far, I have taught two workshops on various occasions. The first is "Talking Neural Networks: A Beginner's Guide", which provides an introduction to the concept of neural networks and provides a guide to some essential machine learning jargon. The second is "Neural Networks for the Wordsmith: An Encounter in Python", which guides workshop participants through building a system in PyTorch to train recurrent neural networks for a classification task. I am currently working on building additional workshops regarding Python and scientific computing.

Education

• Ph.D. Candidate, Computer Science and Engineering
  University of Notre Dame

• B.A., Computer Science
  Xavier University

• Honors B.A., Classics & Philosophy
  Xavier University