BIOGRAPHY
I am interested in programming computers to understand language so that they will be able to perform such tasks as engaging in a natural conversation. This is far beyond our current abilities, so researchers have divided the problem up into manageable research parts. My research focuses on statistical language learning. I write programs that collect statistical information about language from large amounts of text, and then apply the statistics to new examples. I am currently working on statistical models of syntactic parsing-grammatically identifying parts of speech and knowing the rules for sentence formation. This is akin to the sentence diagramming that most of us did in school. Most researchers believe it is a small but important step toward true language understanding. I also research pronoun reference and the automatic learning of facts about words by looking at how they appear in text, known as lexical semantics. My motivation is primarily theoretical: I would simply like to know how language understanding is possible, and most researchers believe that getting a computer to do it would shed a lot of light on the process. However, there are also many applications for this research, including automatic language translation, computer telephone operators, and web search engines that answer questions.
I became interested in computers late in my education as a physics undergraduate at the University of Chicago. I spent the summer between my junior and senior years programming a computer at Argonne National Laboratory for a high-energy physics experiment, and during my senior year I started to read more about computer science. Having originally applied to graduate school in physics, I switched my focus and went to M.I.T. in computer science, where I received my doctorate.
|
