Heterogeneous Graph Neural Networks for Keyphrase Generation

TL;DR

This paper introduces a heterogeneous graph neural network approach that leverages related reference documents to improve keyphrase generation, especially for absent keyphrases, outperforming existing models on benchmark datasets.

Contribution

The paper presents a novel graph-based method incorporating references and a hierarchical attention mechanism to enhance keyphrase generation accuracy.

Findings

Significant improvement in absent keyphrase prediction.

Effective use of reference documents via heterogeneous graphs.

Outperforms baseline models on multiple benchmarks.

Abstract

The encoder-decoder framework achieves state-of-the-art results in keyphrase generation (KG) tasks by predicting both present keyphrases that appear in the source document and absent keyphrases that do not. However, relying solely on the source document can result in generating uncontrollable and inaccurate absent keyphrases. To address these problems, we propose a novel graph-based method that can capture explicit knowledge from related references. Our model first retrieves some document-keyphrases pairs similar to the source document from a pre-defined index as references. Then a heterogeneous graph is constructed to capture relationships of different granularities between the source document and its references. To guide the decoding process, a hierarchical attention and copy mechanism is introduced, which directly copies appropriate words from both the source document and its references based on their relevance and significance. The experimental results on multiple KG benchmarks show that the proposed model achieves significant improvements against other baseline models, especially with regard to the absent keyphrase prediction.