CommonsenseQA: A Question Answering Challenge Targeting Commonsense Knowledge

@article{Talmor2019CommonsenseQAAQ,
  title={CommonsenseQA: A Question Answering Challenge Targeting Commonsense Knowledge},
  author={Alon Talmor and Jonathan Herzig and Nicholas Lourie and Jonathan Berant},
  journal={ArXiv},
  year={2019},
  volume={abs/1811.00937}
}
  • Alon Talmor, Jonathan Herzig, +1 author Jonathan Berant
  • Published 2019
  • Computer Science
  • ArXiv
  • 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
    Language Models as Knowledge Bases?
    • 145
    • PDF
    Social IQA: Commonsense Reasoning about Social Interactions
    • 58
    • PDF
    CommonGen: A Constrained Text Generation Challenge for Generative Commonsense Reasoning.
    • 4
    • PDF
    Explain Yourself! Leveraging Language Models for Commonsense Reasoning
    • 61
    • Highly Influenced
    • PDF
    Unsupervised Commonsense Question Answering with Self-Talk
    • 9
    • Highly Influenced
    • PDF
    KagNet: Knowledge-Aware Graph Networks for Commonsense Reasoning
    • 63
    • Highly Influenced
    • PDF
    Towards Generalizable Neuro-Symbolic Systems for Commonsense Question Answering
    • 10
    • PDF
    Explaining Question Answering Models through Text Generation
    • 6
    • Highly Influenced
    • PDF

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 43 REFERENCES
    SQuAD: 100, 000+ Questions for Machine Comprehension of Text
    • 2,176
    • PDF
    Deep Learning for Answer Sentence Selection
    • 315
    • PDF
    Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge
    • 139
    • PDF
    Improving Language Understanding by Generative Pre-Training
    • 1,434
    • Highly Influential
    • PDF
    Bidirectional Attention Flow for Machine Comprehension
    • 1,151
    • Highly Influential
    • PDF
    A Corpus and Cloze Evaluation for Deeper Understanding of Commonsense Stories
    • 180
    • PDF
    A Simple Method for Commonsense Reasoning
    • 111
    • PDF
    Can a Suit of Armor Conduct Electricity? A New Dataset for Open Book Question Answering
    • 92
    • PDF