NUS at DUC 2006: Document Concept Lattice for Summarization
Shiren Ye, Tat‐Seng Chua · 2006
Concepts composed of open-class terms after semantic equivalence discovery can be considered as simplified basic elements. We utilize frequent concept sets to construct a Document Concept Lattice, which contains hierarchical summary information of a document cluster. Based on this lattice, we further extract a set of sentences with maximal representative power and minimal redundancy for summarization. The implementation of our summarization approach via concept lattice obtains competitive performance in DUC 2006. 1