My research is about solving some of the complex problems that come up in designing systems that access complex documents.
The documents are complex because we look at science and technology research articles and we work on both the text and diagrams in them.
The problems are complex because we don't do just keyword search, we look at the document content, the concepts and ideas in documents. Also, we work on understanding the diagrams in the documents, a difficult problem.
Question: Why do I work on this?
Answer: Because I am first and foremost a scientist, trained in physics
and biology. (Before coming to Northeastern 17 years ago, I was a professor
of biology at the University of Illinois, and before that I worked in physics,
having gotten my PhD in theoretical physics at MIT.) I established the Biological
Knowledge Laboratory here in 1989, the BKL.
How does science work and why is the literature so important? Most of you read books, not what we call the primary scientific literature, the conferences and journals in which the results of research first appear. The primary literature tells us where the "cutting edge" of science is at any moment. It also is the permanent record of what we have learned about the world. Without this literature, we'd have no electricity, cars, planes, computers, antibiotics -- nothing.