# Exploring Graph-structured Passage Representation for Multi-hop Reading Comprehension with Graph Neural Networks

arXiv: https://arxiv.org/abs/1809.02040 · HTML: https://mlsanity.com/paper/1809.02040/

## Key facts

- Cited by 23 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 6 Sep 2018.

## Built on by (most cited first, 23 of 23)

- [Retrieval-Augmented Generation with Graphs (GraphRAG)](https://mlsanity.com/paper/2501.00309/) (2024)
- [Decomposing Complex Questions Makes Multi-Hop QA Easier and More Interpretable](https://mlsanity.com/paper/2110.13472/) (2021)
- [GNN-LM: Language Modeling based on Global Contexts via GNN](https://mlsanity.com/paper/2110.08743/) (2021)
- [GraphSearchNet: Enhancing GNNs via Capturing Global Dependencies for Semantic Code Search](https://mlsanity.com/paper/2111.02671/) (2021)
- [Graph-free Multi-hop Reading Comprehension: A Select-to-Guide Strategy](https://mlsanity.com/paper/2107.11823/) (2021)
- [GLaRA: Graph-based Labeling Rule Augmentation for Weakly Supervised Named Entity Recognition](https://mlsanity.com/paper/2104.06230/) (2021)
- [From Easy to Hard: Two-stage Selector and Reader for Multi-hop Question Answering](https://mlsanity.com/paper/2205.11729/) (2022)
- [Memory Augmented Sequential Paragraph Retrieval for Multi-hop Question Answering](https://mlsanity.com/paper/2102.03741/) (2021)
- [Fact-driven Logical Reasoning for Machine Reading Comprehension](https://mlsanity.com/paper/2105.10334/) (2021)
- [Improving Graph-based Sentence Ordering with Iteratively Predicted Pairwise Orderings](https://mlsanity.com/paper/2110.06446/) (2021)
- [Reasoning Chain Based Adversarial Attack for Multi-hop Question Answering](https://mlsanity.com/paper/2112.09658/) (2021)
- [GNN-SL: Sequence Labeling Based on Nearest Examples via GNN](https://mlsanity.com/paper/2212.02017/) (2022)
- [Interactive Machine Comprehension with Dynamic Knowledge Graphs](https://mlsanity.com/paper/2109.00077/) (2021)
- [Discourse-Aware Graph Networks for Textual Logical Reasoning](https://mlsanity.com/paper/2207.01450/) (2022)
- [Analyzing the Effectiveness of the Underlying Reasoning Tasks in Multi-hop Question Answering](https://mlsanity.com/paper/2302.05963/) (2023)
- [Incorporating Connections Beyond Knowledge Embeddings: A Plug-and-Play Module to Enhance Commonsense Reasoning in Machine Reading Comprehension](https://mlsanity.com/paper/2103.14443/) (2021)
- [Incongruity Detection between Bangla News Headline and Body Content through Graph Neural Network](https://mlsanity.com/paper/2211.07709/) (2022)
- [A Comprehensive Survey on Multi-hop Machine Reading Comprehension Approaches](https://mlsanity.com/paper/2212.04072/) (2022)
- [Graph Attention with Hierarchies for Multi-hop Question Answering](https://mlsanity.com/paper/2301.11792/) (2023)
- [Graph Neural Networks for Natural Language Processing: A Survey](https://mlsanity.com/paper/2106.06090/) (2021)
- [A Hierarchical Entity Graph Convolutional Network for Relation Extraction across Documents](https://mlsanity.com/paper/2108.09505/) (2021)
- [Perturbation-based Active Learning for Question Answering](https://mlsanity.com/paper/2311.02345/) (2023)
- [Algorithm for Semantic Network Generation from Texts of Low Resource Languages Such as Kiswahili](https://mlsanity.com/paper/2501.09326/) (2025)

## Abstract (arXiv)

Multi-hop reading comprehension focuses on one type of factoid question, where a system needs to properly integrate multiple pieces of evidence to correctly answer a question. Previous work approximates global evidence with local coreference information, encoding coreference chains with DAG-styled GRU layers within a gated-attention reader. However, coreference is limited in providing information for rich inference. We introduce a new method for better connecting global evidence, which forms more complex graphs compared to DAGs. To perform evidence integration on our graphs, we investigate two recent graph neural networks, namely graph convolutional network (GCN) and graph recurrent network (GRN). Experiments on two standard datasets show that richer global information leads to better answers. Our method performs better than all published results on these datasets.