My research is focused on natural language processing, machine learning, and artificial intelligence, with a particular interest in the automatic construction of useful knowledge bases from Web text. One of my goals is to develop techniques and prototypes that extend the state of the art in Web search (see for example theKnowItAll project , which I was previously a part of at the University of Washington). Another goal is to theoretically investigate and establish a formal basis for techniques that can learn from unstructured text alone, without hand-labeled data (see for example our papers on a model of redundancy for information extraction and the monotonic feature model for text classification). More generally, I'm interested in ways to utilize human input more effectively in machine learning. Two directions in this effort involve selecting human input carefully (active learning) or utilizing it in concert with unlabeled data (semi-supervised learning).