少花钱多办事：Hypergraph Attention Networks用于归纳文本分类
Be More with Less: Hypergraph Attention Networks for Inductive Text Classification
摘要：
文本分类是自然语言处理中一个重要的研究课题，具有广泛的应用前景。最近，图神经网络（GNNs）在研究界受到越来越多的关注，并在这个典型的任务上展示了他们有前途的结果。尽管取得了成功，但它们的性能在实践中可能会受到很大程度的影响，因为它们：（1）无法捕获单词之间的高阶交互;（2）处理大型数据集和新文档的效率低下。为了解决这些问题，本文提出了一种基于超图注意力网络（Hypergraph Attention Networks，HyperGAT）的文本表示学习模型。在各种基准数据集上的大量实验证明了该方法在文本分类任务上的有效性。
英文摘要：
Text classification is a critical research topic with broad applications in natural language processing. Recently, graph neural networks (GNNs) have received increasing attention in the research community and demonstrated their promising results on this canonical task. Despite the success, their performance could be largely jeopardized in practice since they are: (1) unable to capture high-order interaction between words; (2) inefficient to handle large datasets and new documents. To address those issues, in this paper, we propose a principled model -- hypergraph attention networks (HyperGAT), which can obtain more expressive power with less computational consumption for text representation learning. Extensive experiments on various benchmark datasets demonstrate the efficacy of the proposed approach on the text classification task.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
