Corpus ID: 212413976

Learning to Generate Multi-Hop Knowledge Paths for Commonsense Question Answering

@inproceedings{2020LearningTG,
  title={Learning to Generate Multi-Hop Knowledge Paths for Commonsense Question Answering},
  author={},
  year={2020}
}
  • Published 2020
Commonsense question answering (QA) requires a model of general background knowledge about how the world operates and how people interact with each other before reasoning. Prior works focus primarily on manually curated commonsense knowledge graphs, but these knowledge graphs are incomplete and thus may not contain the necessary knowledge for answering the questions. In this paper, we propose to learn a multi-hop knowledge path generator to generate structured evidence dynamically according to… Expand

Figures and Tables from this paper

References

SHOWING 1-10 OF 30 REFERENCES
HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering
  • 405
  • PDF
CommonsenseQA: A Question Answering Challenge Targeting Commonsense Knowledge
  • 190
  • Highly Influential
  • PDF
KagNet: Knowledge-Aware Graph Networks for Commonsense Reasoning
  • 111
  • PDF
Commonsense Knowledge Base Completion
  • 84
  • PDF
Exploiting Explicit Paths for Multi-hop Reading Comprehension
  • 18
  • PDF
Constructing Datasets for Multi-hop Reading Comprehension Across Documents
  • 239
  • PDF
...
1
2
3
...