Computer Science and Engineering
UC San Diego
Prior to CMU, I received my Bachelor's degree at UC Irvine (zot zot!), where I was a member of the Computation of Language Laboratory (CoLaLab).
My research focuses on natural language processing and machine learning, particularly digital humanities. Currently, I am interested in NLP for historical documents, such as early modern books and manuscript collections, which offer a wealth of information about human history, but can be challenging for modern, data-hungry neural NLP models. For instance, movable type printing press-era books and scribal manuscripts are subject to sources of variation not found in recently printed books or digitized internet text. By collaborating with humanities scholars in the Print and Probablity Project, we try to understand the complex data generating processes and develop novel NLP models with proper inductive biases for the digital humanities.
At CMU, I worked on machine translation with applications to assistive technology for simultaneous interpreters. A couple years earlier, I contributed to a project on multimodal analysis of Parkinson's disease at the Third Frederick Jelinek Memorial Workshop at JHU.
My research has been supported by an NSF Graduate Research Fellowship.
Please see my Google Scholar.
📧 nvogler [-at-] ucsd [-dot-] edu