Heterogeneous Graph Neural Networks for Extractive Document Summarization
This work addresses the problem of improving summarization accuracy for NLP researchers and practitioners, offering a novel graph-based approach that is incremental in enhancing existing methods.
The paper tackles extractive document summarization by introducing a heterogeneous graph neural network (HeterSumGraph) with nodes of different granularities to enrich cross-sentence relations, achieving state-of-the-art results on benchmark datasets like CNN/DailyMail and DUC-2004.
As a crucial step in extractive document summarization, learning cross-sentence relations has been explored by a plethora of approaches. An intuitive way is to put them in the graph-based neural network, which has a more complex structure for capturing inter-sentence relationships. In this paper, we present a heterogeneous graph-based neural network for extractive summarization (HeterSumGraph), which contains semantic nodes of different granularity levels apart from sentences. These additional nodes act as the intermediary between sentences and enrich the cross-sentence relations. Besides, our graph structure is flexible in natural extension from a single-document setting to multi-document via introducing document nodes. To our knowledge, we are the first one to introduce different types of nodes into graph-based neural networks for extractive document summarization and perform a comprehensive qualitative analysis to investigate their benefits. The code will be released on Github