mlsanityData to 7 Oct 2026

Semantic Graphs for Generating Deep Questions

arXiv 2004.12704 ↗First posted 27 Apr 2020cs.CLcited by 38

Not on the map. Why?

Abstract (arXiv)

This paper proposes the problem of Deep Question Generation (DQG), which aims to generate complex questions that require reasoning over multiple pieces of information of the input passage. In order to capture the global structure of the document and facilitate reasoning, we propose a novel framework which first constructs a semantic-level graph for the input document and then encodes the semantic graph by introducing an attention-based GGNN (Att-GGNN). Afterwards, we fuse the document-level and graph-level representations to perform joint training of content selection and question decoding. On the HotpotQA deep-question centric dataset, our model greatly improves performance over questions requiring reasoning over multiple facts, leading to state-of-the-art performance. The code is publicly available at https://github.com/WING-NUS/SG-Deep-Question-Generation.

Key facts. Cited by 38 papers in the map (data through 7 Oct 2026). First posted on arXiv 27 Apr 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 4; 2022: 13; 2023: 7; 2024: 7; 2025: 5; 2026: 2.

38 papers.

Sort:

By area:

  1. 2024Retrieval-Augmented Generation with Graphs (GraphRAG)cited by 170
  2. 2021Zero-shot Fact Verification by Claim Generationcited by 42
  3. 2021Controllable Open-ended Question Generation with A New Question Type Ontologycited by 36
  4. 2021Guiding the Growth: Difficulty-Controllable Question Generation through Step-by-Step Rewritingcited by 30
  5. 2022Generative Language Models for Paragraph-Level Question Generationcited by 28
  6. 2024Learning to Generate Instruction Tuning Datasets for Zero-Shot Task Adaptationcited by 27
  7. 2022Educational Question Generation of Children Storybooks via Question Type Distribution Learning and Event-Centric Summarizationcited by 26
  8. 2022Towards Process-Oriented, Modular, and Versatile Question Generation that Meets Educational Needscited by 19
  9. 2022RQUGE: Reference-Free Metric for Evaluating Question Generation by Answering the Questioncited by 17
  10. 2022Learning to Ask Like a Physiciancited by 16
  11. 2023FOLLOWUPQG: Towards Information-Seeking Follow-up Question Generationcited by 12
  12. 2024Exploring the Capabilities of Prompted Large Language Models in Educational and Assessment Applicationscited by 12
26 more
  1. 2022QRelScore: Better Evaluating Generated Questions with Deeper Understanding of Context-aware Relevancecited by 9
  2. 2022QAScore -- An Unsupervised Unreferenced Metric for the Question Generation Evaluationcited by 9
  3. 2023Few-Shot Data Synthesis for Open Domain Multi-Hop Question Answeringcited by 9
  4. 2023Harnessing the Power of Prompt-based Techniques for Generating School-Level Questions using Large Language Modelscited by 9
  5. 2021Simple or Complex? Complexity-Controllable Question Generation with Soft Templates and Deep Mixture of Experts Modelcited by 8
  6. 2022R5: Rule Discovery with Reinforced and Recurrent Relational Reasoningcited by 7
  7. 2024Explainable Multi-hop Question Generation: An End-to-End Approach without Intermediate Question Labelingcited by 7
  8. 2022QA Is the New KR: Question-Answer Pairs as Knowledge Basescited by 6
  9. 2022Evaluation of Question Answering Systems: Complexity of judging a natural languagecited by 5
  10. 2023Automatic Answerability Evaluation for Question Generationcited by 5
  11. 2024A Survey on Neural Question Generation: Methods, Applications, and Prospectscited by 5
  12. 2022Graph Neural Networks for Multiparallel Word Alignmentcited by 4
  13. 2022QA4QG: Using Question Answering to Constrain Multi-Hop Question Generationcited by 3
  14. 2023The Knowledge Alignment Problem: Bridging Human and External Knowledge for Large Language Modelscited by 3
  15. 2023Exploring the Potential of Large Language Models in Generating Code-Tracing Questions for Introductory Programming Coursescited by 3
  16. 2025Multi-Hop Question Generation via Dual-Perspective Keyword Guidancecited by 3
  17. 2024Reference-based Metrics Disprove Themselves in Question Generationcited by 2
  18. 2024ECIS-VQG: Generation of Entity-centric Information-seeking Questions from Videoscited by 2
  19. 2025Bridging Information Gaps with Comprehensive Answers: Improving the Diversity and Informativeness of Follow-Up Questionscited by 2
  20. 2025KCS: Diversify Multi-hop Question Generation with Knowledge Composition Samplingcited by 2
  21. 2022Enhancing Pre-trained Models with Text Structure Knowledge for Question Generationcited by 1
  22. 2023SkillQG: Learning to Generate Question for Reading Comprehension Assessmentcited by 1
  23. 2025Improving Zero-shot Sentence Decontextualisation with Content Selection and Planningcited by 0
  24. 2025VideoChain: A Transformer-Based Framework for Multi-hop Video Question Generationcited by 0
  25. 2026When Verification Fails: How Compositionally Infeasible Claims Escape Rejectioncited by 0
  26. 2026Exploiting Intrinsic Duality for Multi-Hop Question Generationcited by 0