HEGEL: Hypergraph Transformer for Long Document Summarization
This addresses the problem of modeling long-distance dependencies in document summarization for NLP applications, but it appears incremental as it builds on existing hypergraph and transformer methods.
The paper tackles the challenge of extractive summarization for long documents by proposing HEGEL, a hypergraph neural network that captures high-order cross-sentence relations, and it demonstrates effectiveness and efficiency on two benchmark datasets.
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.