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

@article{Khot2019WhatsMA,
  title={What's Missing: A Knowledge Gap Guided Approach for Multi-hop Question Answering},
  author={Tushar Khot and Ashish Sabharwal and Peter Clark},
  journal={ArXiv},
  year={2019},
  volume={abs/1909.09253}
}
  • Tushar Khot, Ashish Sabharwal, Peter Clark
  • Published in EMNLP 2019
Multi-hop textual question answering requires combining information from multiple sentences. We focus on a natural setting where, unlike typical reading comprehension, only partial information is provided with each question. The model must retrieve and use additional knowledge to correctly answer the question. To tackle this challenge, we develop a novel approach that explicitly identifies the knowledge gap between a key span in the provided knowledge and the answer choices. The model, GapQA… CONTINUE READING

Figures, Tables, Results, and Topics from this paper.

Key Quantitative Results

  • Our model outperforms the previous state-ofthe-art partial knowledge models by 6.5% (64.41 vs 57.93) on a targeted subset of OpenBookQA amenable to gap-based reasoning.

Explore Further: Topics Discussed in This Paper

References

Publications referenced by this paper.
SHOWING 1-10 OF 50 REFERENCES

Constructing Datasets for Multi-hop Reading Comprehension Across Documents

  • Transactions of the Association for Computational Linguistics
  • 2017
VIEW 4 EXCERPTS
HIGHLY INFLUENTIAL