mlsanityData to 7 Oct 2026

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

arXiv 1905.07374 ↗First posted 17 May 2019cs.CLcited by 53

Not on the map. Why?

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.

Key facts. Cited by 53 papers in the map (data through 7 Oct 2026). First posted on arXiv 17 May 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 14; 2022: 23; 2023: 6; 2024: 4; 2025: 1; 2026: 5.

53 papers.

Sort:

By area:

  1. 2022A General Survey on Attention Mechanisms in Deep Learningcited by 64
  2. 2022A Survey of Multi-task Learning in Natural Language Processing: Regarding Task Relatedness and Training Methodscited by 42
  3. 2021Decomposing Complex Questions Makes Multi-Hop QA Easier and More Interpretablecited by 35
  4. 2023CRAB: Assessing the Strength of Causal Relationships Between Real-world Eventscited by 27
  5. 2025PropRAG: Guiding Retrieval with Beam Search over Proposition Pathscited by 22
  6. 2022HeterMPC: A Heterogeneous Graph Neural Network for Response Generation in Multi-Party Conversationscited by 16
  7. 2021Heterogeneous Graph Neural Networks for Keyphrase Generationcited by 15
  8. 2022InducT-GCN: Inductive Graph Convolutional Networks for Text Classificationcited by 15
  9. 2021Complex Factoid Question Answering with a Free-Text Knowledge Graphcited by 14
  10. 2021Graph-free Multi-hop Reading Comprehension: A Select-to-Guide Strategycited by 13
  11. 2022From Easy to Hard: Two-stage Selector and Reader for Multi-hop Question Answeringcited by 12
  12. 2021Learning Reasoning Paths over Semantic Graphs for Video-grounded Dialoguescited by 11
38 more
  1. 2022ME-GCN: Multi-dimensional Edge-Embedded Graph Convolutional Networks for Semi-supervised Text Classificationcited by 10
  2. 2022ReSel: N-ary Relation Extraction from Scientific Text and Tables by Learning to Retrieve and Selectcited by 10
  3. 2024MDCure: A Scalable Pipeline for Multi-Document Instruction-Followingcited by 10
  4. 2021Graph-Based Tri-Attention Network for Answer Ranking in CQAcited by 8
  5. 2021Topological Regularization for Graph Neural Networks Augmentationcited by 8
  6. 2024SEAM: A Stochastic Benchmark for Multi-Document Taskscited by 8
  7. 2022Beyond the Granularity: Multi-Perspective Dialogue Collaborative Selection for Dialogue State Trackingcited by 6
  8. 2022Locate Then Ask: Interpretable Stepwise Reasoning for Multi-hop Question Answeringcited by 6
  9. 2024FSM: A Finite State Machine Based Zero-Shot Prompting Paradigm for Multi-Hop Question Answeringcited by 6
  10. 2021Coarse-grained decomposition and fine-grained interaction for multi-hop question answeringcited by 5
  11. 2022Graph Neural Networks: a bibliometrics overviewcited by 5
  12. 2023HOP, UNION, GENERATE: Explainable Multi-hop Reasoning without Rationale Supervisioncited by 5
  13. 2021Memory Augmented Sequential Paragraph Retrieval for Multi-hop Question Answeringcited by 4
  14. 2021Reasoning Chain Based Adversarial Attack for Multi-hop Question Answeringcited by 4
  15. 2022Understanding Graph Convolutional Networks for Text Classificationcited by 4
  16. 2022IMCI: Integrate Multi-view Contextual Information for Fact Extraction and Verificationcited by 3
  17. 2022Context-Aware Query Rewriting for Improving Users' Search Experience on E-commerce Websitescited by 3
  18. 2023LUKE-Graph: A Transformer-based Approach with Gated Relational Graph Attention for Cloze-style Reading Comprehensioncited by 3
  19. 2021Ensemble Learning-Based Approach for Improving Generalization Capability of Machine Reading Comprehension Systemscited by 2
  20. 2022Ask to Understand: Question Generation for Multi-hop Question Answeringcited by 2
  21. 2022Discourse-Aware Graph Networks for Textual Logical Reasoningcited by 2
  22. 2022Getting the Most out of Simile Recognitioncited by 2
  23. 2022IRRGN: An Implicit Relational Reasoning Graph Network for Multi-turn Response Selectioncited by 2
  24. 2023Analyzing the Effectiveness of the Underlying Reasoning Tasks in Multi-hop Question Answeringcited by 2
  25. 2024SG-FSM: A Self-Guiding Zero-Shot Prompting Paradigm for Multi-Hop Question Answering Based on Finite State Machinecited by 2
  26. 2021ClueReader: Heterogeneous Graph Attention Network for Multi-hop Machine Reading Comprehensioncited by 1
  27. 2022How Well Do Multi-hop Reading Comprehension Models Understand Date Information?cited by 1
  28. 2022Relational Graph Convolutional Neural Networks for Multihop Reasoning: A Comparative Studycited by 1
  29. 2022A Comprehensive Survey on Multi-hop Machine Reading Comprehension Approachescited by 1
  30. 2022Medical Knowledge Graph QA for Drug-Drug Interaction Prediction based on Multi-hop Machine Reading Comprehensioncited by 1
  31. 2023Graph Attention with Hierarchies for Multi-hop Question Answeringcited by 1
  32. 2023Integrating a Heterogeneous Graph with Entity-aware Self-attention using Relative Position Labels for Reading Comprehension Modelcited by 1
  33. 2026KEPo: Knowledge Evolution Poison on Graph-based Retrieval-Augmented Generationcited by 1
  34. 2021Deep Neural Networks for Relation Extractioncited by 0
  35. 2021Does Structure Matter? Leveraging Data-to-Text Generation for Answering Complex Information Needscited by 0
  36. 2022elBERto: Self-supervised Commonsense Learning for Question Answeringcited by 0
  37. 2022Syntax-informed Question Answering with Heterogeneous Graph Transformercited by 0
  38. 2026SemEval-2026 Task 12: Abductive Event Reasoning: Towards Real-World Event Causal Inference for Large Language Modelscited by 0

50 most cited of 53 All 53 (JSON)