Corpus ID: 17799567

Investigation of Language Understanding Impact for Reinforcement Learning Based Dialogue Systems

@article{Li2017InvestigationOL,
  title={Investigation of Language Understanding Impact for Reinforcement Learning Based Dialogue Systems},
  author={Xiujun Li and Yun-Nung Chen and Lihong Li and Jianfeng Gao and Asli Çelikyilmaz},
  journal={ArXiv},
  year={2017},
  volume={abs/1703.07055}
}
  • Xiujun Li, Yun-Nung Chen, +2 authors Asli Çelikyilmaz
  • Published 2017
  • Computer Science
  • ArXiv
  • Language understanding is a key component in a spoken dialogue system. In this paper, we investigate how the language understanding module influences the dialogue system performance by conducting a series of systematic experiments on a task-oriented neural dialogue system in a reinforcement learning based setting. The empirical study shows that among different types of language understanding errors, slot-level errors can have more impact on the overall performance of a dialogue system compared… CONTINUE READING

    Figures, Tables, and Topics from this paper.

    Explore key concepts

    Links to highly relevant papers for key concepts in this paper:

    Citations

    Publications citing this paper.
    SHOWING 1-10 OF 21 CITATIONS

    Sample Efficient Deep Reinforcement Learning for Dialogue Systems With Large Action Spaces

    VIEW 1 EXCERPT
    CITES BACKGROUND

    Open-Domain Neural Dialogue Systems

    VIEW 2 EXCERPTS
    CITES BACKGROUND

    Deep Learning for Dialogue Systems

    VIEW 4 EXCERPTS
    CITES BACKGROUND

    Deep Active Learning for Dialogue Generation

    VIEW 2 EXCERPTS
    CITES BACKGROUND

    Neural Approaches to Conversational AI

    VIEW 5 EXCERPTS
    CITES METHODS & BACKGROUND

    FILTER CITATIONS BY YEAR

    2017
    2020

    CITATION STATISTICS

    • 1 Highly Influenced Citations

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 28 REFERENCES

    User modeling for spoken dialogue system evaluation

    VIEW 1 EXCERPT

    Error simulation for training statistical dialogue systems

    VIEW 1 EXCERPT

    End-to-end joint learning of natural language understanding and dialogue manager

    VIEW 2 EXCERPTS

    The Hidden Agenda User Simulation Model

    VIEW 1 EXCERPT

    Consistent Goal-Directed User Model for Realisitc Man-Machine Task-Oriented Spoken Dialogue Simulation

    • Olivier Pietquin
    • Computer Science
    • 2006 IEEE International Conference on Multimedia and Expo
    • 2006
    VIEW 1 EXCERPT