Corpus ID: 202734545

Technical report on Conversational Question Answering

@article{Ju2019TechnicalRO,
  title={Technical report on Conversational Question Answering},
  author={Ying Ju and Fubang Zhao and Shijie Chen and Bowen Zheng and Xuefeng Yang and Yunfeng Liu},
  journal={ArXiv},
  year={2019},
  volume={abs/1909.10772}
}
  • Ying Ju, Fubang Zhao, +3 authors Yunfeng Liu
  • Published in ArXiv 2019
  • Computer Science
  • Conversational Question Answering is a challenging task since it requires understanding of conversational history. In this project, we propose a new system RoBERTa + AT +KD, which involves rationale tagging multi-task, adversarial training, knowledge distillation and a linguistic post-process strategy. Our single model achieves 90.4(F1) on the CoQA test set without data augmentation, outperforming the current state-of-the-art single model by 2.6% F1. 

    Create an AI-powered research feed to stay up to date with new papers like this posted to ArXiv

    Figures, Tables, and Topics from this paper.

    Citations

    Publications citing this paper.

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 22 REFERENCES

    CoQA: A Conversational Question Answering Challenge

    VIEW 4 EXCERPTS
    HIGHLY INFLUENTIAL

    Virtual Adversarial Training for Semi-Supervised Text Classification

    VIEW 4 EXCERPTS
    HIGHLY INFLUENTIAL

    Born-Again Neural Networks

    VIEW 3 EXCERPTS
    HIGHLY INFLUENTIAL

    Decoupled Weight Decay Regularization

    VIEW 1 EXCERPT