Her research is focused on capturing elements of the meanings of words that can comprise automatic representations of complex sentences and documents. In artificial intelligence, supervised machine learning techniques rely on vast amounts of annotated training data, so she and her students have provided data with semantic annotation for English, Chinese, Arabic, Korean, Hindi, and Urdu, funded by DARPA and NSF, both manually and automatically. A more recent focus is the application of these methods to biomedical journal articles and clinical notes, funded by NIH, and the geosciences, funded by NSF. She co-edits LiLT, Linguistic Issues in Language Technology, and has been a co-editor of Natural Language Engineering and on the Computational Linguistics Editorial Board. She has well over 300 reviewed publications.