Multi-Document Summarization Model Based on Redundancy-Constrained Knapsack Problem

Abstract

In this paper we propose a novel text summarization model, the redundancy-constrained knapsack model. We add to the Knapsack problem a constraint to curb redundancy in the summary. We also propose a fast decoding method based on the Lagrange heuristic. Experiments based on ROUGE evaluations show that our proposals outperform a state-of-the-art text summarization model, the maximum coverage model, in finding the optimal solution. We also show that our decoding method quickly finds a good approximate solution comparable to the optimal solution of the maximum coverage model.