Enhancing Machine Reading Comprehension With Position Information

@article{Xu2019EnhancingMR,
  title={Enhancing Machine Reading Comprehension With Position Information},
  author={Yajing Xu and Weijie Liu and Guang Chen and Boya Ren and Siman Zhang and Sheng Gao and Jun Guo},
  journal={IEEE Access},
  year={2019},
  volume={7},
  pages={141602-141611}
}
When people do the reading comprehension, they often try to find the words from the passages which are similar to the question words first. Then people deduce the answer based on the context around these similar words. Therefore, the position information may be helpful in finding the answer rapidly and is useful for reading comprehension. However, previous attention-based machine reading comprehension models typically focus on the interaction between the question and the context representation… CONTINUE READING

Figures, Tables, and Topics from this paper.

Explore Further: Topics Discussed in This Paper

References

Publications referenced by this paper.
SHOWING 1-10 OF 39 REFERENCES

Long Short-Term Memory

  • Neural Computation
  • 1997
VIEW 6 EXCERPTS
HIGHLY INFLUENTIAL

Position-aware Attention for Enhancing the Machine Comprehension

  • 2018 International Conference on Network Infrastructure and Digital Content (IC-NIDC)
  • 2018
VIEW 3 EXCERPTS
HIGHLY INFLUENTIAL

Attention is All you Need

VIEW 3 EXCERPTS
HIGHLY INFLUENTIAL

Gatedattention readers for text comprehension

B. Dhingra, H. Liu, Z. Yang, W. W. Cohen, R. Salakhutdinov
  • Proc. 55th Annu. Meeting Assoc. Comput. Linguistics, vol. 1, 2017, pp. 1–15.
  • 2017
VIEW 1 EXCERPT