ResearchTrend.AI
  • Papers
  • Communities
  • Events
  • Blog
  • Pricing
Papers
Communities
Social Events
Terms and Conditions
Pricing
Parameter LabParameter LabTwitterGitHubLinkedInBlueskyYoutube

© 2025 ResearchTrend.AI, All rights reserved.

  1. Home
  2. Papers
  3. 1808.04926
17
231

How Much Reading Does Reading Comprehension Require? A Critical Investigation of Popular Benchmarks

14 August 2018
Divyansh Kaushik
Zachary Chase Lipton
    ELM
ArXivPDFHTML
Abstract

Many recent papers address reading comprehension, where examples consist of (question, passage, answer) tuples. Presumably, a model must combine information from both questions and passages to predict corresponding answers. However, despite intense interest in the topic, with hundreds of published papers vying for leaderboard dominance, basic questions about the difficulty of many popular benchmarks remain unanswered. In this paper, we establish sensible baselines for the bAbI, SQuAD, CBT, CNN, and Who-did-What datasets, finding that question- and passage-only models often perform surprisingly well. On 141414 out of 202020 bAbI tasks, passage-only models achieve greater than 50%50\%50% accuracy, sometimes matching the full model. Interestingly, while CBT provides 202020-sentence stories only the last is needed for comparably accurate prediction. By comparison, SQuAD and CNN appear better-constructed.

View on arXiv
Comments on this paper