Looking Beyond the Surface: A Challenge Set for Reading Comprehension over Multiple Sentences

  title={Looking Beyond the Surface: A Challenge Set for Reading Comprehension over Multiple Sentences},
  author={Daniel Khashabi and S. Chaturvedi and Michael Roth and Shyam Upadhyay and D. Roth},
  • Daniel Khashabi, S. Chaturvedi, +2 authors D. Roth
  • Published in NAACL-HLT 2018
  • Computer Science
  • We present a reading comprehension challenge in which questions can only be answered by taking into account information from multiple sentences. [...] Key Result The dataset is the first to study multi-sentence inference at scale, with an open-ended set of question types that requires reasoning skills.Expand Abstract
    Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer
    • 469
    • Open Access
    CoQA: A Conversational Question Answering Challenge
    • 283
    • Open Access
    HuggingFace's Transformers: State-of-the-art Natural Language Processing
    • 685
    • Open Access
    SuperGLUE: A Stickier Benchmark for General-Purpose Language Understanding Systems
    • 184
    • Open Access
    Can a Suit of Armor Conduct Electricity? A New Dataset for Open Book Question Answering
    • 88
    • Open Access
    DREAM: A Challenge Data Set and Models for Dialogue-Based Reading Comprehension
    • 49
    • Open Access
    Improving Machine Reading Comprehension with General Reading Strategies
    • 59
    • Highly Influenced
    • Open Access
    Dual Co-Matching Network for Multi-choice Reading Comprehension
    • 34
    • Open Access


    Publications referenced by this paper.
    SQuAD: 100, 000+ Questions for Machine Comprehension of Text
    • 2,125
    • Highly Influential
    • Open Access
    Teaching Machines to Read and Comprehend
    • 1,630
    • Open Access
    Towards AI-Complete Question Answering: A Set of Prerequisite Toy Tasks
    • 737
    • Open Access
    Bidirectional Attention Flow for Machine Comprehension
    • 1,131
    • Open Access
    MCTest: A Challenge Dataset for the Open-Domain Machine Comprehension of Text
    • 448
    • Highly Influential
    • Open Access
    TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension
    • 457
    • Open Access
    Adversarial Examples for Evaluating Reading Comprehension Systems
    • 600
    • Open Access
    MS MARCO: A Human Generated MAchine Reading COmprehension Dataset
    • 501
    • Open Access
    WikiQA: A Challenge Dataset for Open-Domain Question Answering
    • 442
    • Open Access
    A Thorough Examination of the CNN/Daily Mail Reading Comprehension Task
    • 402
    • Open Access