Derek is a Research Scientist working on designing intelligent dialogue systems with stronger natural language understanding. His research is focused on efficiently training NLP models in low resource settings including data augmentation, data denoising, and few-shot learning. He is also interested in techniques surrounding uncertainty measurement so that a dialogue agent can better manage ambiguity and out-of-scope situations. He ultimately believes that a data-centric view of machine learning will usher in a wave of much more useful services than what we see today.

Derek started his research journey at the Stanford NLP Lab, working on negotiation dialogues. He eventually graduated with a masters in Computer Science from the University of Washington, while working on data collection at UW NLP. He is currently advised by Prof. Zhou Yu at Columbia University, where he continues his journey on studying the intersection of dialogue systems and data efficiency.

This blog is about the journey in building a qualitatively superior virtual assistant and the start-up surrounding this product. Specifically, the assistant will focus on listening rather than responding, understanding rather than reacting. In other words, the assistant will move beyond executing commands and towards conversations that last more than one turn.