Corpus ID: 211482559

COMMONGEN: Towards Generative Commonsense Reasoning via A Constrained Text Generation Challenge

@inproceedings{Lin2020COMMONGENTG,
  title={COMMONGEN: Towards Generative Commonsense Reasoning via A Constrained Text Generation Challenge},
  author={Bill Yuchen Lin and Minghan Shen and Yu Xing and Pei Zhou and Xiang Ren},
  year={2020}
}
Given a set of common concepts like “{apple (noun), pick (verb), tree (noun)}”, humans find it easy to write a sentence describing a grammatical and logically coherent scenario that covers these concepts, for example: “a boy picks an apple from a tree”. The process of generating these sentences requires humans to use commonsense knowledge. We denote this ability as generative commonsense reasoning. Recent work in commonsense reasoning has focused mainly on discriminating the most plausible… Expand

Figures and Tables from this paper

References

SHOWING 1-10 OF 61 REFERENCES
CommonsenseQA: A Question Answering Challenge Targeting Commonsense Knowledge
  • 194
  • Highly Influential
  • PDF
Cosmos QA: Machine Reading Comprehension with Contextual Commonsense Reasoning
  • 86
  • PDF
Commonsense Reasoning for Natural Language Understanding: A Survey of Benchmarks, Resources, and Approaches
  • 30
  • PDF
KagNet: Knowledge-Aware Graph Networks for Commonsense Reasoning
  • 114
  • PDF
Commonsense Knowledge Aware Conversation Generation with Graph Attention
  • 197
  • PDF
GQA: A New Dataset for Real-World Visual Reasoning and Compositional Question Answering
  • 218
  • PDF
CODAH: An Adversarially Authored Question-Answer Dataset for Common Sense
  • 20
  • PDF
ATOMIC: An Atlas of Machine Commonsense for If-Then Reasoning
  • 201
  • PDF
ConceptNet 5.5: An Open Multilingual Graph of General Knowledge
  • 735
  • PDF
...
1
2
3
4
5
...