Introduction to Cross-Document Coreference


Cross-Document Coreference occurs when the same person, place, event, or
concept is referenced more than once in multiple sources. The resolution of
cross-document coreference is useful for a number of higher level tasks such
as cross-document summarization and information extraction.

The talk will attempt to provide an introduction to the field of
cross-document coreference. It will first put the problem into perspective
by comparing it with other natural language tasks. Next, an overview of the
different methodologies will be provided. This will be followed by a
discussion of evaluation issues and algorithms. Finally, a number of
different applications of cross-document coreference including cross-media
coreference, cross-language coreference, and cross-document information
extraction will be discussed.


Amit Bagga is Chief Scientist and Head of Research of Comcast's Search and
Discovery Division, StreamSage.  Previously, he managed the Vertical Search
and Natural Language Processing Groups at Ask.com.  Prior to that he was a
researcher at Avaya Labs and GE's Global Research Labs.  Dr. Bagga received
his Ph.D. From Duke University in 1998.