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

TL;DR

This paper introduces a novel heterogeneous graph model for multi-hop reading comprehension across multiple documents, enabling reasoning over diverse information types and achieving state-of-the-art results on WikiHop.

Contribution

The paper presents a new Heterogeneous Document-Entity graph model with GNN-based reasoning for multi-hop RC, improving over previous single-document approaches.

Findings

Single model achieves competitive results on WikiHop.

Ensemble model sets new state-of-the-art performance.

Effective reasoning over heterogeneous information types.

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.