Attentive History Selection for Conversational Question Answering

@article{Qu2019AttentiveHS,
  title={Attentive History Selection for Conversational Question Answering},
  author={Chen Qu and Liu Yang and Minghui Qiu and Yongfeng Zhang and Cen Chen and W. Bruce Croft and Mohit Iyyer},
  journal={Proceedings of the 28th ACM International Conference on Information and Knowledge Management},
  year={2019}
}
  • Chen Qu, Liu Yang, +4 authors Mohit Iyyer
  • Published 2019
  • Computer Science
  • Proceedings of the 28th ACM International Conference on Information and Knowledge Management
  • Conversational question answering (ConvQA) is a simplified but concrete setting of conversational search. One of its major challenges is to leverage the conversation history to understand and answer the current question. In this work, we propose a novel solution for ConvQA that involves three aspects. First, we propose a positional history answer embedding method to encode conversation history with position information using BERT in a natural way. BERT is a powerful technique for text… CONTINUE READING

    Figures, Tables, and Topics from this paper.

    Citations

    Publications citing this paper.
    SHOWING 1-10 OF 13 CITATIONS

    Open-Retrieval Conversational Question Answering

    VIEW 3 EXCERPTS
    CITES BACKGROUND & RESULTS

    A Survey of Document Grounded Dialogue Systems (DGDS)

    VIEW 18 EXCERPTS
    CITES BACKGROUND, METHODS & RESULTS
    HIGHLY INFLUENCED

    Survey on evaluation methods for dialogue systems

    VIEW 1 EXCERPT
    CITES BACKGROUND

    References

    Publications referenced by this paper.
    SHOWING 1-9 OF 9 REFERENCES

    CoQA: A Conversational Question Answering Challenge

    VIEW 10 EXCERPTS
    HIGHLY INFLUENTIAL

    M

    • M. Sankar
    • Edinburgh Medical and Surgical Journal
    • 1824
    VIEW 10 EXCERPTS
    HIGHLY INFLUENTIAL

    SQuAD: 100

    • P. Rajpurkar, J. Zhang, K. Lopyrev, P. Liang
    • 000+ Questions for Machine Comprehension of Text. In EMNLP
    • 2016
    VIEW 8 EXCERPTS
    HIGHLY INFLUENTIAL