I am a computational linguist with research focuses on accessibility for Natural Language Processing, including representation for minority languages, and fairness and ethics in natural language processing (NLP).
Most recently, I was appointed as faculty in the Linguistics Department at the University of Washington, where I taught in the Master of Science in Computational Linguistics program (CLMS).
My dissertation research focused on writing the INterlinear Text ENrichment Toolkit, (INTENT) — a tool designed to bootstrap linguistic knowledge for basic NLP tasks using extracts from linguistics papers as a proxy for expert annotation. Via the Online Database for INterlinear text (ODIN), INTENT supports upwards of 1,500 languages.
As part of the RiPLes project, I have worked on a variety of tools related to data extraction of multilingual documents from PDF, including language identification, passage and document classification, and even PDF-to-text analysis for academic linguistic papers.