Statistical Models for Information Extraction for REFLEX (DARPA/BBN)

Principal Investigator:

Andrew McCallum, PI

Information Extraction and Synthesis Laboratory (IESL)/
Center for Intelligent Information Retrieval (CIIR)
Department of Computer Science
140 Governors Drive
University of Massachusetts
Amherst, MA 01003-9264

In this project, UMass Amherst is a subcontractor to BBN Technologies on a DARPA-sponsored project to develop statistical models for information extraction that combine many sources of information in novel, integrated ways. UMass Amherst will develop, implement, and evaluate a new component that models entity mentions and coreference in an integrated fashion, making use of contextural information from the rest of the document and perhaps beyond. In addition, the UMass team will develop, implement, and evaluate a model that predicts relations in a similarly integrated way and will extend the integrated model to predict events along with coreference and relations.