mlsanityData to 7 Oct 2026

Reinforcement Learning Based Graph-to-Sequence Model for Natural Question Generation

arXiv 1908.04942 ↗First posted 14 Aug 2019cs.CLcited by 57

Not on the map. Why?

Abstract (arXiv)

Natural question generation (QG) aims to generate questions from a passage and an answer. Previous works on QG either (i) ignore the rich structure information hidden in text, (ii) solely rely on cross-entropy loss that leads to issues like exposure bias and inconsistency between train/test measurement, or (iii) fail to fully exploit the answer information. To address these limitations, in this paper, we propose a reinforcement learning (RL) based graph-to-sequence (Graph2Seq) model for QG. Our model consists of a Graph2Seq generator with a novel Bidirectional Gated Graph Neural Network based encoder to embed the passage, and a hybrid evaluator with a mixed objective combining both cross-entropy and RL losses to ensure the generation of syntactically and semantically valid text. We also introduce an effective Deep Alignment Network for incorporating the answer information into the passage at both the word and contextual levels. Our model is end-to-end trainable and achieves new state-of-the-art scores, outperforming existing methods by a significant margin on the standard SQuAD benchmark.

Key facts. Cited by 57 papers in the map (data through 7 Oct 2026). First posted on arXiv 14 Aug 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2020: 1; 2021: 11; 2022: 17; 2023: 16; 2024: 7; 2025: 3; 2026: 2.

57 papers.

Sort:

By area:

  1. 2023A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questionscited by 1,582
  2. 2022Why Exposure Bias Matters: An Imitation Learning Perspective of Error Accumulation in Language Generationcited by 106
  3. 2020Retrieval-Augmented Generation for Code Summarization via Hybrid GNNcited by 89
  4. 2022Automatic Generation of Socratic Subquestions for Teaching Math Word Problemscited by 42
  5. 2021Reinforced Neighborhood Selection Guided Multi-Relational Graph Neural Networkscited by 38
  6. 2023Task-Optimized Adapters for an End-to-End Task-Oriented Dialogue Systemcited by 30
  7. 2023The Expressive Power of Graph Neural Networks: A Surveycited by 27
  8. 2021Heterogeneous Global Graph Neural Networks for Personalized Session-based Recommendationcited by 22
  9. 2023Data-centric Graph Learning: A Surveycited by 22
  10. 2021Improving Unsupervised Question Answering via Summarization-Informed Question Generationcited by 21
  11. 2022EdgeFormer: A Parameter-Efficient Transformer for On-Device Seq2seq Generationcited by 21
  12. 2022Compact Graph Structure Learning via Mutual Information Compressioncited by 20
38 more
  1. 2021Bridging the Gap between Spatial and Spectral Domains: A Unified Framework for Graph Neural Networkscited by 18
  2. 2022Reinforcement learning on graphs: A surveycited by 18
  3. 2021ReGen: Reinforcement Learning for Text and Knowledge Base Generation using Pretrained Language Modelscited by 16
  4. 2021GraphSearchNet: Enhancing GNNs via Capturing Global Dependencies for Semantic Code Searchcited by 15
  5. 2022Orders Are Unwanted: Dynamic Deep Graph Convolutional Network for Personality Detectioncited by 14
  6. 2021Relation-aware Graph Attention Model With Adaptive Self-adversarial Trainingcited by 12
  7. 2023MinPrompt: Graph-based Minimal Prompt Data Augmentation for Few-shot Question Answeringcited by 12
  8. 2021Re-evaluating Word Mover's Distancecited by 10
  9. 2022TrustGNN: Graph Neural Network based Trust Evaluation via Learnable Propagative and Composable Naturecited by 10
  10. 2023PVG: Progressive Vision Graph for Vision Recognitioncited by 10
  11. 2023Universal Representation of Permutation-Invariant Functions on Vectors and Tensorscited by 10
  12. 2023Diversify Question Generation with Retrieval-Augmented Style Transfercited by 10
  13. 2022TegTok: Augmenting Text Generation via Task-specific and Open-world Knowledgecited by 9
  14. 2022QRelScore: Better Evaluating Generated Questions with Deeper Understanding of Context-aware Relevancecited by 9
  15. 2022QAScore -- An Unsupervised Unreferenced Metric for the Question Generation Evaluationcited by 9
  16. 2024Beyond the Federation: Topology-aware Federated Learning for Generalization to Unseen Clientscited by 7
  17. 2021HAConvGNN: Hierarchical Attention Based Convolutional Graph Neural Network for Code Documentation Generation in Jupyter Notebookscited by 6
  18. 2024Dr.Academy: A Benchmark for Evaluating Questioning Capability in Education for Large Language Modelscited by 6
  19. 2022What Functions Can Graph Neural Networks Generate?cited by 5
  20. 2022Downstream Transformer Generation of Question-Answer Pairs with Preprocessing and Postprocessing Pipelinescited by 5
  21. 2022Combining Data Generation and Active Learning for Low-Resource Question Answeringcited by 5
  22. 2023Proactive and Reactive Engagement of Artificial Intelligence Methods for Education: A Reviewcited by 5
  23. 2023DoubleH: Twitter User Stance Detection via Bipartite Graph Neural Networkscited by 4
  24. 2026DiffusionRollout: Uncertainty-Aware Rollout Planning in Long-Horizon PDE Solvingcited by 4
  25. 2022Robust Graph Structure Learning via Multiple Statistical Testscited by 3
  26. 2022Deep representation learning: Fundamentals, Perspectives, Applications, and Open Challengescited by 3
  27. 2025Multi-Hop Question Generation via Dual-Perspective Keyword Guidancecited by 3
  28. 2023Automatic Generation of Multiple-Choice Questionscited by 2
  29. 2024Increasing the Difficulty of Automatically Generated Questions via Reinforcement Learning with Synthetic Preferencecited by 2
  30. 2024ECIS-VQG: Generation of Entity-centric Information-seeking Questions from Videoscited by 2
  31. 2021Triples-to-Text Generation with Reinforcement Learning Based Graph-augmented Neural Networkscited by 1
  32. 2022Sequential Search with Off-Policy Reinforcement Learningcited by 1
  33. 2022Enhancing Pre-trained Models with Text Structure Knowledge for Question Generationcited by 1
  34. 2023SkillQG: Learning to Generate Question for Reading Comprehension Assessmentcited by 1
  35. 2023Knowledge Graph for NLG in the context of conversational agentscited by 1
  36. 2023Mitigating the Exposure Bias in Sentence-Level Grapheme-to-Phoneme (G2P) Transductioncited by 1
  37. 2023Prompt-Engineering and Transformer-based Question Generation and Evaluationcited by 1
  38. 2024Synergizing Machine Learning & Symbolic Methods: A Survey on Hybrid Approaches to Natural Language Processingcited by 1

50 most cited of 57 All 57 (JSON)