• Computer Science
  • Published in NAACL-HLT 2019

CommonsenseQA: A Question Answering Challenge Targeting Commonsense Knowledge

@inproceedings{Talmor2019CommonsenseQAAQ,
  title={CommonsenseQA: A Question Answering Challenge Targeting Commonsense Knowledge},
  author={Alon Talmor and Jonathan Herzig and Nicholas Lourie and Jonathan Berant},
  booktitle={NAACL-HLT},
  year={2019}
}
When answering a question, people often draw upon their rich world knowledge in addition to some task-specific context. [...] Key Result Our best baseline, the OpenAI GPT (Radford et al., 2018), obtains 54.8% accuracy, well below human performance, which is 95.3%.Expand Abstract

Citations

Publications citing this paper.
SHOWING 1-10 OF 41 CITATIONS

FREELB: ENHANCED ADVERSARIAL TRAINING FOR NATURAL LANGUAGE UNDERSTANDING

  • 2019
VIEW 9 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

FreeLB: Enhanced Adversarial Training for Language Understanding

VIEW 9 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

Unifying Question Answering and Text Classification via Span Extraction

VIEW 6 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

Commonsense Properties from Query Logs and Question Answering Forums

VIEW 16 EXCERPTS
CITES METHODS
HIGHLY INFLUENCED

ERASER: A Benchmark to Evaluate Rationalized NLP Models

VIEW 7 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

References

Publications referenced by this paper.
SHOWING 1-10 OF 39 REFERENCES

Improving Language Understanding by Generative Pre-Training

VIEW 7 EXCERPTS
HIGHLY INFLUENTIAL

The Winograd Schema Challenge

VIEW 4 EXCERPTS
HIGHLY INFLUENTIAL

From Recognition to Cognition: Visual Commonsense Reasoning

VIEW 7 EXCERPTS
HIGHLY INFLUENTIAL