Semantic Graphs for Generating Deep Questions

@inproceedings{Pan2020SemanticGF,
  title={Semantic Graphs for Generating Deep Questions},
  author={Liangming Pan and Yuxi Xie and Yansong Feng and Tat-Seng Chua and Min-Yen Kan},
  booktitle={ACL},
  year={2020}
}
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… Expand
11 Citations

Figures and Tables from this paper

Stronger Transformers for Neural Multi-Hop Question Generation
  • Highly Influenced
  • PDF
Answer-driven Deep Question Generation based on Reinforcement Learning
  • Highly Influenced
  • PDF
Asking Complex Questions with Multi-hop Answer-focused Reasoning
  • Highly Influenced
  • PDF
A Hierarchical Reasoning Graph Neural Network for The Automatic Scoring of Answer Transcriptions in Video Job Interviews
  • Highly Influenced
  • PDF
Accelerating Real-Time Question Answering via Question Generation
  • 4
  • Highly Influenced
  • PDF
Frame Semantics guided network for Abstractive Sentence Summarization
  • Yong Guan, Shaoru Guo, Ru Li, Xiaoli Li, Hu Zhang
  • Computer Science
  • 2021
A Survey of Knowledge-Enhanced Text Generation
  • 5
  • PDF
Knowledge Base Question Answering through Recursive Hypergraphs
  • PDF
Exploring Question-Specific Rewards for Generating Deep Questions
  • PDF
...
1
2
...

References

SHOWING 1-10 OF 39 REFERENCES
Question Answering by Reasoning Across Documents with Graph Convolutional Networks
  • 106
  • PDF
Improving Neural Question Generation using Answer Separation
  • 63
  • Highly Influential
  • PDF
HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering
  • 418
  • PDF
Question Generation for Question Answering
  • 124
  • PDF
Neural Question Generation from Text: A Preliminary Study
  • 161
  • PDF
Paragraph-level Neural Question Generation with Maxout Pointer and Gated Self-attention Networks
  • 118
  • PDF
Learning to Generate Questions by LearningWhat not to Generate
  • 30
  • Highly Influential
  • PDF
Learning to Ask: Neural Question Generation for Reading Comprehension
  • 298
  • Highly Influential
  • PDF
Towards Automatic Topical Question Generation
  • 25
  • PDF
...
1
2
3
4
...