Can a Suit of Armor Conduct Electricity? A New Dataset for Open Book Question Answering

@inproceedings{Mihaylov2018CanAS,
  title={Can a Suit of Armor Conduct Electricity? A New Dataset for Open Book Question Answering},
  author={Todor Mihaylov and Peter Clark and Tushar Khot and Ashish Sabharwal},
  booktitle={EMNLP},
  year={2018}
}
We present a new kind of question answering dataset, OpenBookQA, modeled after open book exams for assessing human understanding of a subject. [...] Key Result Our oracle experiments designed to circumvent the knowledge retrieval bottleneck demonstrate the value of both the open book and additional facts. We leave it as a challenge to solve the retrieval problem in this multi-hop setting and to close the large gap to human performance.Expand Abstract

Figures, Tables, and Topics from this paper.

Citations

Publications citing this paper.
SHOWING 1-10 OF 48 CITATIONS

What's Missing: A Knowledge Gap Guided Approach for Multi-hop Question Answering

VIEW 9 EXCERPTS
CITES BACKGROUND, METHODS & RESULTS

An Effective Multi-Stage Approach For Question Answering

  • 2019
VIEW 7 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

What Does My QA Model Know? Devising Controlled Probes using Expert Knowledge

VIEW 5 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

Improving Machine Reading Comprehension with General Reading Strategies

VIEW 4 EXCERPTS
CITES BACKGROUND
HIGHLY INFLUENCED

Improving Natural Language Inference Using External Knowledge in the Science Questions Domain

VIEW 4 EXCERPTS
CITES RESULTS, BACKGROUND & METHODS
HIGHLY INFLUENCED

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

VIEW 4 EXCERPTS
CITES BACKGROUND
HIGHLY INFLUENCED

Exploiting Explicit Paths for Multi-hop Reading Comprehension

VIEW 4 EXCERPTS
CITES BACKGROUND & RESULTS

References

Publications referenced by this paper.
SHOWING 1-10 OF 49 REFERENCES

Annotation Artifacts in Natural Language Inference Data

VIEW 4 EXCERPTS
HIGHLY INFLUENTIAL

Enhanced LSTM for Natural Language Inference

VIEW 5 EXCERPTS
HIGHLY INFLUENTIAL

Deep contextualized word representations

VIEW 2 EXCERPTS
HIGHLY INFLUENTIAL

Constructing Datasets for Multi-hop Reading Comprehension Across Documents

VIEW 3 EXCERPTS
HIGHLY INFLUENTIAL