SummPip: Unsupervised Multi-Document Summarization with Sentence Graph Compression

TL;DR

SummPip introduces an unsupervised multi-document summarization approach that constructs sentence graphs, clusters, and compresses sentences, achieving competitive results without requiring labeled training data.

Contribution

It presents a novel unsupervised framework combining sentence graph construction, spectral clustering, and compression for multi-document summarization.

Findings

Competitive performance on Multi-News and DUC-2004 datasets

Comparable to supervised neural models in quality

Produces consistent and complete summaries according to human evaluation

Abstract

Obtaining training data for multi-document summarization (MDS) is time consuming and resource-intensive, so recent neural models can only be trained for limited domains. In this paper, we propose SummPip: an unsupervised method for multi-document summarization, in which we convert the original documents to a sentence graph, taking both linguistic and deep representation into account, then apply spectral clustering to obtain multiple clusters of sentences, and finally compress each cluster to generate the final summary. Experiments on Multi-News and DUC-2004 datasets show that our method is competitive to previous unsupervised methods and is even comparable to the neural supervised approaches. In addition, human evaluation shows our system produces consistent and complete summaries compared to human written ones.