Corpus ID: 53116060

U-Net: Machine Reading Comprehension with Unanswerable Questions

@article{Sun2018UNetMR,
  title={U-Net: Machine Reading Comprehension with Unanswerable Questions},
  author={F. Sun and L. Li and Xipeng Qiu and Y. Liu},
  journal={ArXiv},
  year={2018},
  volume={abs/1810.06638}
}
  • F. Sun, L. Li, +1 author Y. Liu
  • Published 2018
  • Computer Science
  • ArXiv
  • Machine reading comprehension with unanswerable questions is a new challenging task for natural language processing. A key subtask is to reliably predict whether the question is unanswerable. In this paper, we propose a unified model, called U-Net, with three important components: answer pointer, no-answer pointer, and answer verifier. We introduce a universal node and thus process the question and its context passage as a single contiguous sequence of tokens. The universal node encodes the… CONTINUE READING
    Relation Module for Non-answerable Prediction on Question Answering
    Question Answering with Hierarchical Attention Fusion Layers & MultiTask Learning
    Relation Module for Non-Answerable Predictions on Reading Comprehension
    1
    EQuANt (Enhanced Question Answer Network)
    Multi-style Generative Reading Comprehension
    23
    SQuAD : Eliminate What You Don ’ t Know
    SG-Net: Syntax-Guided Machine Reading Comprehension
    26

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 41 REFERENCES
    Learning Recurrent Span Representations for Extractive Question Answering
    107
    SQuAD: 100, 000+ Questions for Machine Comprehension of Text
    2030