BoolQ: Exploring the Surprising Difficulty of Natural Yes/No Questions

By Christopher Clark, Kenton C. T. Lee, Ming-Wei Chang, Tom Kwiatkowski, Michael Collins, Kristina Toutanova. 2019

2,559 citations recorded by the source corpus.

In this paper we study yes/no questions that are naturally occurring — meaning that they are generated in unprompted and unconstrained settings. We build a reading comprehension dataset, BoolQ, of such questions, and show that they are unexpectedly challenging. They often query for complex, non-factoid information, and require difficult entailment-like inference to solve. We also explore the effectiveness of a range of transfer learning baselines. We find that transferring from entailment data is more effective than transferring from paraphrase or extractive QA data, and that it, surprisingly, continues to be very beneficial even when starting from massive pre-trained language models such as BERT. Our best method trains BERT on MultiNLI and then re-trains it on our train set. It achieves 80.4% accuracy compared to 90% accuracy of human annotators (and 62% majority-baseline), leaving a significant gap for future work.

Subfields: Artificial Intelligence, General Social Sciences, Natural Language Processing, Evaluation & Benchmarks

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

  1. Mohit Bansal
  2. Luke S. Zettlemoyer
  3. Percy Liang
  4. Jianfeng Gao
  5. Yejin Choi
  6. Hannaneh Hajishirzi
  7. Noah A. Smith
  8. Graham Neubig

In General Social Sciences

  1. Arman Cohan
  2. Daniel Khashabi
  3. Yonatan Belinkov
  4. Tushar Khot
  5. Luke S. Zettlemoyer
  6. Ashish Sabharwal
  7. Matt Gardner
  8. Dan Roth

In Natural Language Processing

  1. Mohit Bansal
  2. Luke S. Zettlemoyer
  3. Yejin Choi
  4. Hannaneh Hajishirzi
  5. Graham Neubig
  6. Percy Liang
  7. Noah A. Smith
  8. Jianfeng Gao

In Evaluation & Benchmarks

  1. Mohit Bansal
  2. Yejin Choi
  3. Hannaneh Hajishirzi
  4. Luke S. Zettlemoyer
  5. Samuel R. Bowman
  6. Matt Gardner
  7. Ashish Sabharwal
  8. Greg Durrett

Citations in the corpus