Multi-document abstractive summarization using ILP based multi-sentence compression

TL;DR

This paper presents a novel multi-document abstractive summarization method that uses ILP to select the most informative and readable sentences from generated paths, outperforming existing methods on standard datasets.

Contribution

The paper introduces an ILP-based multi-sentence compression approach that effectively combines sentence clustering, shortest path generation, and optimization for improved abstractive summarization.

Findings

Outperforms state-of-the-art extractive and abstractive methods on DUC datasets.

Achieves higher ROUGE scores indicating better summary quality.

Manual evaluation shows improved informativeness and readability.

Abstract

Abstractive summarization is an ideal form of summarization since it can synthesize information from multiple documents to create concise informative summaries. In this work, we aim at developing an abstractive summarizer. First, our proposed approach identifies the most important document in the multi-document set. The sentences in the most important document are aligned to sentences in other documents to generate clusters of similar sentences. Second, we generate K-shortest paths from the sentences in each cluster using a word-graph structure. Finally, we select sentences from the set of shortest paths generated from all the clusters employing a novel integer linear programming (ILP) model with the objective of maximizing information content and readability of the final summary. Our ILP model represents the shortest paths as binary variables and considers the length of the path, information score and linguistic quality score in the objective function. Experimental results on the DUC 2004 and 2005 multi-document summarization datasets show that our proposed approach outperforms all the baselines and state-of-the-art extractive summarizers as measured by the ROUGE scores. Our method also outperforms a recent abstractive summarization technique. In manual evaluation, our approach also achieves promising results on informativeness and readability.