HEGEL: Hypergraph Transformer for Long Document Summarization

TL;DR

HEGEL introduces a hypergraph transformer model that effectively captures complex cross-sentence relations for improved long document extractive summarization, demonstrating superior performance on benchmark datasets.

Contribution

This paper presents HEGEL, a novel hypergraph neural network that models high-order sentence relations for the first time in long document summarization.

Findings

HEGEL outperforms existing methods on benchmark datasets.

HEGEL effectively captures diverse sentence dependencies.

HEGEL demonstrates both effectiveness and efficiency.

Abstract

Extractive summarization for long documents is challenging due to the extended structured input context. The long-distance sentence dependency hinders cross-sentence relations modeling, the critical step of extractive summarization. This paper proposes HEGEL, a hypergraph neural network for long document summarization by capturing high-order cross-sentence relations. HEGEL updates and learns effective sentence representations with hypergraph transformer layers and fuses different types of sentence dependencies, including latent topics, keywords coreference, and section structure. We validate HEGEL by conducting extensive experiments on two benchmark datasets, and experimental results demonstrate the effectiveness and efficiency of HEGEL.