Detecting Sub-Topic Correspondence through Bipartite Term Clustering

Abstract

This paper addresses a novel task of detecting sub-topic correspondence in a pair of text fragments, enhancing common notions of text similarity. This task is addressed by coupling corresponding term subsets through bipartite clustering. The paper presents a cost-based clustering scheme and compares it with a bipartite version of the single-link method, providing illustrating results.

html with 3 gif figures; generated from 7 pages MS-Word file