Jacob A. Matthews

I’m a PhD candidate in Romance Studies with a minor in Cognitive Science at Cornell. I received my BA in French and Francophone Studies from Columbia in 2019.

Broadly speaking, I’m interested in applying computational and experimental methods within the humanities, particularly in literary and area studies.

My current research areas include:

• representational analysis of language and embedding models
• differences between human and machine language processing
• literary theory (Gilles Deleuze, Michel Serres) and cognition.

My graduate committee is Laurent Dubreuil (chair), Morten Christiansen, and Shimon Edelman.

I also collaborate with people in:

• C.Psyd
• Humanities Lab at Cornell
• Cornell NLP

Some recent and ongoing projects:

• “Semantics or spelling? Probing contextual word embeddings with orthographic noise”. Jacob A. Matthews, John R. Starr and Marten van Schijndel. Findings of the ACL 2024. (paper) (poster) (slides)
• “Enhancing Language Model Representations with Attributed Network Embeddings”, PEER 2024. (slides)
• “An embarrassingly simple method for attributed network embedding”. Jacob A. Matthews, Imane Terhmina, Laurent Dubreuil and Marten van Schijndel. New Directions in Analyzing Text as Data, 2023. (poster)
• “Grokking Wug Vectors”. Jacob A. Matthews and Marten van Schijndel. 36th Annual Conference on Human Sentence Processing, 2023. (abstract) (poster)