Simple and Effective Curriculum Pointer-Generator Networks for Reading Comprehension over Long Narratives

@article{Tay2019SimpleAE,
  title={Simple and Effective Curriculum Pointer-Generator Networks for Reading Comprehension over Long Narratives},
  author={Yi Tay and Shuohang Wang and Anh Tuan Luu and Jie Fu and Minh C. Phan and Xingdi Yuan and Jinfeng Rao and Siu Cheung Hui and Aston Zhang},
  journal={ArXiv},
  year={2019},
  volume={abs/1905.10847}
}
  • Yi Tay, Shuohang Wang, +6 authors Aston Zhang
  • Published 2019
  • Computer Science
  • ArXiv
  • This paper tackles the problem of reading comprehension over long narratives where documents easily span over thousands of tokens. We propose a curriculum learning (CL) based Pointer-Generator framework for reading/sampling over large documents, enabling diverse training of the neural model based on the notion of alternating contextual difficulty. This can be interpreted as a form of domain randomization and/or generative pretraining during training. To this end, the usage of the Pointer… CONTINUE READING

    Citations

    Publications citing this paper.
    SHOWING 1-9 OF 9 CITATIONS

    Curriculum Learning for Natural Language Understanding

    VIEW 8 EXCERPTS
    CITES BACKGROUND & METHODS
    HIGHLY INFLUENCED

    Extractive NarrativeQA with Heuristic Pre-Training

    VIEW 4 EXCERPTS
    CITES BACKGROUND & METHODS
    HIGHLY INFLUENCED

    Frustratingly Hard Evidence Retrieval for QA Over Books

    VIEW 6 EXCERPTS
    CITES METHODS & BACKGROUND
    HIGHLY INFLUENCED

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 71 REFERENCES

    The NarrativeQA Reading Comprehension Challenge

    VIEW 21 EXCERPTS
    HIGHLY INFLUENTIAL

    The NarrativeQA Reading Comprehension Challenge

    VIEW 21 EXCERPTS
    HIGHLY INFLUENTIAL