Corpus ID: 3922816

Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge

@article{Clark2018ThinkYH,
  title={Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge},
  author={Peter Clark and Isaac Cowhey and Oren Etzioni and Tushar Khot and A. Sabharwal and Carissa Schoenick and Oyvind Tafjord},
  journal={ArXiv},
  year={2018},
  volume={abs/1803.05457}
}
  • Peter Clark, Isaac Cowhey, +4 authors Oyvind Tafjord
  • Published 2018
  • Computer Science
  • ArXiv
  • We present a new question set, text corpus, and baselines assembled to encourage AI research in advanced question answering. [...] Key Method The dataset contains only natural, grade-school science questions (authored for human tests), and is the largest public-domain set of this kind (7,787 questions). We test several baselines on the Challenge Set, including leading neural models from the SQuAD and SNLI tasks, and find that none are able to significantly outperform a random baseline, reflecting the difficult…Expand Abstract

    Figures, Tables, and Topics from this paper.

    Answering Science Exam Questions Using Query Rewriting with Background Knowledge
    • 5
    • Highly Influenced
    • PDF
    Answering Science Exam Questions Using Query Reformulation with Background Knowledge
    • 5
    • Highly Influenced
    KG^2: Learning to Reason Science Exam Questions with Contextual Knowledge Graph Embeddings
    • 15
    • Highly Influenced
    • PDF
    Reasoning-Driven Question-Answering for Natural Language Understanding
    A Systematic Classification of Knowledge, Reasoning, and Context within the ARC Dataset
    • 19
    • Highly Influenced
    • PDF
    Improving Retrieval-Based Question Answering with Deep Inference Models
    • 5
    • PDF
    Advances in Automatically Solving the ENEM
    Advances in Automatically Solving the ENEM
    • 1

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 30 REFERENCES
    Towards AI-Complete Question Answering: A Set of Prerequisite Toy Tasks
    • 742
    • PDF
    Question Answering via Integer Programming over Semi-Structured Knowledge
    • 66
    • PDF
    Question Answering as Global Reasoning Over Semantic Abstractions
    • 43
    • PDF
    SciTaiL: A Textual Entailment Dataset from Science Question Answering
    • 148
    MCTest: A Challenge Dataset for the Open-Domain Machine Comprehension of Text
    • 454
    • PDF
    Combining Retrieval, Statistics, and Inference to Answer Elementary Science Questions
    • 94
    • PDF
    Query-Reduction Networks for Question Answering
    • 89
    • Highly Influential
    • PDF
    SQuAD: 100, 000+ Questions for Machine Comprehension of Text
    • 2,163
    • Highly Influential
    • PDF
    NewsQA: A Machine Comprehension Dataset
    • 320
    • PDF