Referent tracking (RT) is a new paradigm, based on unique identification, for representing and keeping track of particulars. It was first introduced to support the entry and retri...
: Image understanding often requires extensive background knowledge. The problem addressed in this paper is such knowledge can be acquired. We discuss how relational machine learni...
In this paper, we propose a statistical approach for clustering of artMes using on-line dictionary definitions. One of the characteristics of our approach is that every sense of w...
We consider the problem of producing a multi-document summary given a collection of documents. Since most successful methods of multi-document summarization are still largely extr...
John M. Conroy, Judith D. Schlesinger, Dianne P. O...
This paper introduces a number of general methods for visualizing commonality in sets of text files. Each visualization simultaneously compares one file in the set to all other ...