There is precisely one complete language processing system to date: the human brain.  Though there is debate on how much built-in bias human learners might have, we definitely acquire language in a primarily unsupervised fashion. Computational approaches to language processing, however, are almost exclusively supervised, relying on hand-labeled corpora for training. In this program, Dan Klein describes several syntactic representations designed to capture the basic character of natural language syntax as directly as possible. High-quality parses can be learned from surprisingly little text, with no labeled examples and no language-specific biases. From the Series:CSE Colloquia - 2004