Unsupervised Multi-document Summarization with Holistic Inference

TL;DR

This paper introduces a novel unsupervised multi-document summarization framework that uses holistic inference and a new diversity measure called SRI, significantly improving summary quality and diversity.

Contribution

It presents a holistic beam search inference method with the Subset Representative Index (SRI) for unsupervised extractive summarization, emphasizing diversity and importance.

Findings

Outperforms strong baselines in ROUGE scores

Demonstrates the importance of diversity in summaries

Effective on both small and large datasets

Abstract

Multi-document summarization aims to obtain core information from a collection of documents written on the same topic. This paper proposes a new holistic framework for unsupervised multi-document extractive summarization. Our method incorporates the holistic beam search inference method associated with the holistic measurements, named Subset Representative Index (SRI). SRI balances the importance and diversity of a subset of sentences from the source documents and can be calculated in unsupervised and adaptive manners. To demonstrate the effectiveness of our method, we conduct extensive experiments on both small and large-scale multi-document summarization datasets under both unsupervised and adaptive settings. The proposed method outperforms strong baselines by a significant margin, as indicated by the resulting ROUGE scores and diversity measures. Our findings also suggest that diversity is essential for improving multi-document summary performance.