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

arXiv: https://arxiv.org/abs/1905.07374 · HTML: https://mlsanity.com/paper/1905.07374/

## Key facts

- Cited by 53 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 May 2019.

## Built on by (most cited first, 30 of 53)

- [A General Survey on Attention Mechanisms in Deep Learning](https://mlsanity.com/paper/2203.14263/) (2022)
- [A Survey of Multi-task Learning in Natural Language Processing: Regarding Task Relatedness and Training Methods](https://mlsanity.com/paper/2204.03508/) (2022)
- [Decomposing Complex Questions Makes Multi-Hop QA Easier and More Interpretable](https://mlsanity.com/paper/2110.13472/) (2021)
- [CRAB: Assessing the Strength of Causal Relationships Between Real-world Events](https://mlsanity.com/paper/2311.04284/) (2023)
- [PropRAG: Guiding Retrieval with Beam Search over Proposition Paths](https://mlsanity.com/paper/2504.18070/) (2025)
- [HeterMPC: A Heterogeneous Graph Neural Network for Response Generation in Multi-Party Conversations](https://mlsanity.com/paper/2203.08500/) (2022)
- [Heterogeneous Graph Neural Networks for Keyphrase Generation](https://mlsanity.com/paper/2109.04703/) (2021)
- [InducT-GCN: Inductive Graph Convolutional Networks for Text Classification](https://mlsanity.com/paper/2206.00265/) (2022)
- [Complex Factoid Question Answering with a Free-Text Knowledge Graph](https://mlsanity.com/paper/2103.12876/) (2021)
- [Graph-free Multi-hop Reading Comprehension: A Select-to-Guide Strategy](https://mlsanity.com/paper/2107.11823/) (2021)
- [From Easy to Hard: Two-stage Selector and Reader for Multi-hop Question Answering](https://mlsanity.com/paper/2205.11729/) (2022)
- [Learning Reasoning Paths over Semantic Graphs for Video-grounded Dialogues](https://mlsanity.com/paper/2103.00820/) (2021)
- [ME-GCN: Multi-dimensional Edge-Embedded Graph Convolutional Networks for Semi-supervised Text Classification](https://mlsanity.com/paper/2204.04618/) (2022)
- [ReSel: N-ary Relation Extraction from Scientific Text and Tables by Learning to Retrieve and Select](https://mlsanity.com/paper/2210.14427/) (2022)
- [MDCure: A Scalable Pipeline for Multi-Document Instruction-Following](https://mlsanity.com/paper/2410.23463/) (2024)
- [Graph-Based Tri-Attention Network for Answer Ranking in CQA](https://mlsanity.com/paper/2103.03583/) (2021)
- [Topological Regularization for Graph Neural Networks Augmentation](https://mlsanity.com/paper/2104.02478/) (2021)
- [SEAM: A Stochastic Benchmark for Multi-Document Tasks](https://mlsanity.com/paper/2406.16086/) (2024)
- [Beyond the Granularity: Multi-Perspective Dialogue Collaborative Selection for Dialogue State Tracking](https://mlsanity.com/paper/2205.10059/) (2022)
- [Locate Then Ask: Interpretable Stepwise Reasoning for Multi-hop Question Answering](https://mlsanity.com/paper/2208.10297/) (2022)
- [FSM: A Finite State Machine Based Zero-Shot Prompting Paradigm for Multi-Hop Question Answering](https://mlsanity.com/paper/2407.02964/) (2024)
- [Coarse-grained decomposition and fine-grained interaction for multi-hop question answering](https://mlsanity.com/paper/2101.05988/) (2021)
- [Graph Neural Networks: a bibliometrics overview](https://mlsanity.com/paper/2201.01188/) (2022)
- [HOP, UNION, GENERATE: Explainable Multi-hop Reasoning without Rationale Supervision](https://mlsanity.com/paper/2305.14237/) (2023)
- [Memory Augmented Sequential Paragraph Retrieval for Multi-hop Question Answering](https://mlsanity.com/paper/2102.03741/) (2021)
- [Reasoning Chain Based Adversarial Attack for Multi-hop Question Answering](https://mlsanity.com/paper/2112.09658/) (2021)
- [Understanding Graph Convolutional Networks for Text Classification](https://mlsanity.com/paper/2203.16060/) (2022)
- [IMCI: Integrate Multi-view Contextual Information for Fact Extraction and Verification](https://mlsanity.com/paper/2208.14001/) (2022)
- [Context-Aware Query Rewriting for Improving Users' Search Experience on E-commerce Websites](https://mlsanity.com/paper/2209.07584/) (2022)
- [LUKE-Graph: A Transformer-based Approach with Gated Relational Graph Attention for Cloze-style Reading Comprehension](https://mlsanity.com/paper/2303.06675/) (2023)

## Abstract (arXiv)

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.