Detecting Sub-Topic Correspondence through Bipartite Term Clustering
Computation and Language
2007-05-23 v1
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.
Cite
@article{arxiv.cs/9908001,
title = {Detecting Sub-Topic Correspondence through Bipartite Term Clustering},
author = {Zvika Marx and Ido Dagan and Eli Shamir},
journal= {arXiv preprint arXiv:cs/9908001},
year = {2007}
}
Comments
html with 3 gif figures; generated from 7 pages MS-Word file