Organizing the implicit topology of a document as a graph, and further performing feature extraction via the graph convolutional network (GCN), has proven effective in document analysis. However, existing document graphs are often restricted to expressing single-level relations, which are predefined and independent of downstream learning. A set of learnable hierarchical graphs are built to explore multilevel sentence relations, assisted by a hierarchical probabilistic topic model. Based on these graphs, multiple parallel GCNs are used to extract multilevel semantic features, which are aggregated by an attention mechanism for different document-comprehension tasks. Equipped with variational inference, the graph construction and GCN are learned jointly, allowing the graphs to evolve dynamically to better match the downstream task. The effectiveness and efficiency of the proposed multilevel sentence relation graph convolutional network (MuserGCN) is demonstrated via experiments on document classification, abstractive summarization, and matching.

中文翻译：

---

从多级句子关系中学习分层文档图

将文档的隐式拓扑组织为图，并通过图卷积网络（GCN）进一步执行特征提取，在文档分析中已被证明是有效的。然而，现有的文档图通常仅限于表达单层关系，这些关系是预定义的并且独立于下游学习。在分层概率主题模型的帮助下，构建了一组可学习的分层图来探索多级句子关系。基于这些图，使用多个并行 GCN 来提取多级语义特征，这些特征通过注意机制针对不同的文档理解任务进行聚合。配备变分推理，图构建和 GCN 是联合学习的，允许图动态演化以更好地匹配下游任务。通过文档分类、抽象摘要和匹配的实验证明了所提出的多级句子关系图卷积网络（MuserGCN）的有效性和效率。