Learning in Natural Language

Dan Roth
Dept. of Computer Science and the Beckman Institute
University of Illinois - Urbana/Champaign

In language understanding related tasks inferences heavily depend on knowledge about the language and the world. I will present research on a learning centered approach to performing these kind of ``knowledge-intensive inferences''.

First, I will present a learning theory account of the major statistical approaches to learning in natural language and explain why they work although, typically, the assumptions they are based on do not hold in the data. Then I will present our own SNoW learning architecture and discuss how it is used to support large-scale inference problems. The emphasis is on a learning architecture and algorithms that tolerate data of high dimensionality, support relational knowledge representations and allow the incorporation of additional knowledge into the process. The approach will be exemplified with experimental evidence from a diverse collection of language understanding related tasks.