Graph Sequential Network for Reasoning over Sequences
arXiv:2004.02001
Abstract
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.
Part of this paper was presented at NeurIPS 2019 Workshop on Graph Representation Learning
References in corpus (5)
- Semi-Supervised Classification with Graph Convolutional Networks
- Coarse-grain Fine-grain Coattention Network for Multi-evidence Question Answering
- Dynamically Fused Graph Network for Multi-hop Reasoning
- Select, Answer and Explain: Interpretable Multi-hop Reading Comprehension over Multiple Documents
- Compositional Questions Do Not Necessitate Multi-hop Reasoning