用图注意力网络增强文本摘要，但简单MLP更有效。
Text Summarization With Graph Attention Networks
- 用RST和共指图结构建模文本关系
- MLP在CNN/DM数据集上提升摘要效果
- 标注XSum数据集为后续研究提供基准
本研究旨在利用图信息（特别是修辞结构理论RST和共指关系Coref图）来提升基线摘要模型的性能。我们尝试采用图注意力网络架构融合图信息，但未见性能提升。随后改用简单的多层感知机架构，在主要数据集CNN/DM上取得了更好的结果。此外，我们对XSum数据集进行了RST图标注，建立了未来基于图的摘要模型的基准。该次级数据集带来了多重挑战，揭示了所提模型的优势与局限性。
原文摘要 · Abstract (English)
This study aimed to leverage graph information, particularly Rhetorical Structure Theory (RST) and Co-reference (Coref) graphs, to enhance the performance of our baseline summarization models. Specifically, we experimented with a Graph Attention Network architecture to incorporate graph information. However, this architecture did not enhance the performance. Subsequently, we used a simple Multi-layer Perceptron architecture, which improved the results in our proposed model on our primary dataset, CNN/DM. Additionally, we annotated XSum dataset with RST graph information, establishing a benchmark for future graph-based summarization models. This secondary dataset posed multiple challenges, revealing both the merits and limitations of our models.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。