Skip to main content

Pierrehumbert Language Modelling Group

Pierrehumbert Language Modelling Group


Photograph of Janet Pierrehumbert by Ian Wallman

Our group develops and applies methods in computational linguistics and natural language processing (NLP) to address a variety of questions about linguistic patterns in human communities. We are interested in creating robust and beneficial language technology, and also in formalizing and testing theories in the language sciences. These goals go hand-in-hand. We use classical algorithms, deep learning models, and experimental data to address them.

We are particularly interested in approaches that:

  • Are anchored in what is known about linguistic systems, and about how humans acquire them and deploy them in language processing.
  • Succeed in handling language variation across different times, topics, and social contexts.
  • Make forecasts or predictions that are consequential and interpretable.