Answers are grounded in this paper and cite their sources.
Demonstrates improved text summarization in comparison models, indicating effectiveness of graph-based methods.
Automatic text summarization is the refinement of text content. Traditional methods simply treat text as a sequence and use encoders such as RNN to learn text semantic features. These methods cannot utilize the grammatical structure information implicit in the text, resulting in low accuracy of summarization generated by the model. In this paper, we use dependency graphs to represent text and use Gated Graph Neural Networks as encoder, which makes it easier to learn long-distance dependencies between nodes. It obtains the feature vectors of the text dependency graph based on the hidden states of nodes, and finally uses the Transformer decoder to generate text summarization. Experimental results show that the model performance is better than the selected comparison model.
No takes yet. Share an insight, caveat, or question.
Yu et al. (2023) studied this question.
Synapse has enriched 8 closely related papers on similar clinical questions. Consider them for comparative context: