Joint Turn and Dialogue level User Satisfaction Estimation on Multi-Domain Conversations

@article{Bodigutla2020JointTA,
  title={Joint Turn and Dialogue level User Satisfaction Estimation on Multi-Domain Conversations},
  author={Praveen Kumar Bodigutla and Aditya Tiwari and Josep Valls-Vargas and L. Polymenakos and Spyridon Matsoukas},
  journal={ArXiv},
  year={2020},
  volume={abs/2010.02495}
}
  • Praveen Kumar Bodigutla, Aditya Tiwari, +2 authors Spyridon Matsoukas
  • Published 2020
  • Computer Science
  • ArXiv
  • Dialogue level quality estimation is vital for optimizing data driven dialogue management. Current automated methods to estimate turn and dialogue level user satisfaction employ hand-crafted features and rely on complex annotation schemes, which reduce the generalizability of the trained models. We propose a novel user satisfaction estimation approach which minimizes an adaptive multi-task loss function in order to jointly predict turn-level Response Quality labels provided by experts and… CONTINUE READING

    Figures and Tables from this paper

    References

    SHOWING 1-10 OF 37 REFERENCES
    Domain-Independent turn-level Dialogue Quality Evaluation via User Satisfaction Estimation
    • 3
    • PDF
    Multi-domain Conversation Quality Evaluation via User Satisfaction Estimation
    • 4
    • PDF
    Learning from real users: rating dialogue success with neural networks for reinforcement learning in spoken dialogue systems
    • 56
    • PDF
    Improving Interaction Quality Estimation with BiLSTMs and the Impact on Dialogue Policy Learning
    • 4
    • PDF
    Ordinal regression for interaction quality prediction
    • 15
    • PDF
    Application and Evaluation of a Conditioned Hidden Markov Model for Estimating Interaction Quality of Spoken Dialogue Systems
    • 14
    A Parameterized and Annotated Spoken Dialog Corpus of the CMU Let's Go Bus Information System
    • 72
    • Highly Influential
    • PDF
    Sentiment Adaptive End-to-End Dialog Systems
    • 32
    • PDF