Multi-hop Reading Comprehension across Multiple Documents by Reasoning over Heterogeneous Graphs

Abstract

Multi-hop reading comprehension (RC) across documents poses new challenge over single-document RC because it requires reasoning over multiple documents to reach the final answer. In this paper, we propose a new model to tackle the multi-hop RC problem. We introduce a heterogeneous graph with different types of nodes and edges, which is named as Heterogeneous Document-Entity (HDE) graph. The advantage of HDE graph is that it contains different granularity levels of information including candidates, documents and entities in specific document contexts. Our proposed model can do reasoning over the HDE graph with nodes representation initialized with co-attention and self-attention based context encoders. We employ Graph Neural Networks (GNN) based message passing algorithms to accumulate evidences on the proposed HDE graph. Evaluated on the blind test set of the Qangaroo WikiHop data set, our HDE graph based single model delivers competitive result, and the ensemble model achieves the state-of-the-art performance.

To appear in ACL 2019

References in corpus (10)

• Semi-Supervised Classification with Graph Convolutional Networks
• Inductive Representation Learning on Large Graphs
• Neural Message Passing for Quantum Chemistry
• Dynamic Coattention Networks For Question Answering
• How Powerful are Graph Neural Networks?
• Graph Convolutional Networks for Text Classification
• Coarse-grain Fine-grain Coattention Network for Multi-evidence Question Answering
• Densely Connected Attention Propagation for Reading Comprehension
• Global-to-local Memory Pointer Networks for Task-Oriented Dialogue
• WikiReading: A Novel Large-scale Language Understanding Task over Wikipedia

Cited by in corpus (10)

• A General Survey on Attention Mechanisms in Deep Learning
• Multi-hop Question Answering via Reasoning Chains
• Heterogeneous Graph Neural Networks for Extractive Document Summarization
• Improving Graph Attention Networks with Large Margin-based Constraints
• Graph-Based Reasoning over Heterogeneous External Knowledge for Commonsense Question Answering
• Answering Complex Open-Domain Questions with Multi-Hop Dense Retrieval
• Deep Neural Networks for Relation Extraction
• Tensor Graph Convolutional Networks for Text Classification
• Asking Complex Questions with Multi-hop Answer-focused Reasoning
• Fine-tuning Multi-hop Question Answering with Hierarchical Graph Network