I am an academic—which is to say, a professional nerd. Specifically, a computer nerd and a language nerd. I am interested in human language from the angles of cognition, description, and computation. My expertise is in empirical approaches to computational linguistics (CL—applying computational methods to the study of language) and natural language processing (NLP—building technologies that reason intelligently about language). To analyze natural language text, my work employs a medley of methods from linguistics, data science, and machine learning.

Within CL/NLP, my focus is on computational semantics and natural language understanding. This encompasses the design of meaning representations; human annotation of corpora; and statistical computational modeling. I look for ways to make datasets, models, and tools more informative, accurate, multilingual, robust, and practical. For example: developing tools that work for informal social media language, not just news articles.

At Georgetown, I lead interdisciplinary courses and research in the Linguistics and Computer Science departments, as well as advising students in both departments. My lab is called NERT.