Natural language processing involves the automated extraction of information from written or spoken human languages. With the rise of the internet, social scientists have more data than ever before and most of it consists of unstructured text. The purpose of this program is to provide: (a) a clearinghouse for textual data of interest to social scientists, (b) a central repository for software to analyze textual data, (c) support for the development of new methods of data collection and analysis, and (d) information about new developments and trends in the field of statistical natural language processing. The program also works to foster interdisciplinary research and teaching.

Contact the Executive Director for more information about this program.