论文标题
用于推理序列推理的图顺序网络
Graph Sequential Network for Reasoning over Sequences
论文作者
论文摘要
最近，图形神经网络（GNN）已成功应用于需要推理的各种NLP任务，例如多跳机阅读理解。在本文中，我们考虑了一种新的案例，其中需要对从序列构建的图（即带有序列数据的图形节点）进行推理。现有的GNN模型通过首先将节点序列汇总到固定维矢量中，然后在这些向量上应用GNN来实现此目标。为了避免早期摘要中固有的信息丢失，并在GNN输出上进行顺序标记任务，我们提出了一种新型的GNN，称为Graph Sequential Network（GSN），该GNN具有基于节点和每个邻居之间的共同注意的新消息传递算法的新消息。我们在两个NLP任务上验证了提出的GSN：对HOTPOTQA和基于图的发烧事实验证的可解释的多跳阅读理解。这两个任务都需要通过多个文档或句子进行推理。我们的实验结果表明，所提出的GSN比基于标准GNN的方法的性能更好。
Recently Graph Neural Network (GNN) has been applied successfully to various NLP tasks that require reasoning, such as multi-hop machine reading comprehension. In this paper, we consider a novel case where reasoning is needed over graphs built from sequences, i.e. graph nodes with sequence data. Existing GNN models fulfill this goal by first summarizing the node sequences into fixed-dimensional vectors, then applying GNN on these vectors. To avoid information loss inherent in the early summarization and make sequential labeling tasks on GNN output feasible, we propose a new type of GNN called Graph Sequential Network (GSN), which features a new message passing algorithm based on co-attention between a node and each of its neighbors. We validate the proposed GSN on two NLP tasks: interpretable multi-hop reading comprehension on HotpotQA and graph based fact verification on FEVER. Both tasks require reasoning over multiple documents or sentences. Our experimental results show that the proposed GSN attains better performance than the standard GNN based methods.
