Reding Comprehension Challenges

Back to Blog

This list aims to be a minimal list of RC challenges/datasets that a new system should measure themselves on.

  • Squad: Stanford Question Answering Dataset
  • Marco: Microsoft Machine Reading Comprehension Dataset
  • Natural Questions: Open Domain Question Answering
  • NarrativeQA: The NarrativeQA Reading Comprehension Challenge
  • Qangaroo: Reading comprehenstion with multiple hops
  • MultiRc: Reading Comprehension over Multiple Sentences
  • wikiqa: A Challenge Dataset for Open-Domain Question Answering
  • HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering
  • PiQA: Phrase Indexed Question Answering
  • RACE: Large-scale ReAding Comprehension Dataset From Examination