A Copy-Augmented Sequence-to-Sequence Architecture Gives Good Performance on Task-Oriented Dialogue

@inproceedings{Manning2017ACS,
  title={A Copy-Augmented Sequence-to-Sequence Architecture Gives Good Performance on Task-Oriented Dialogue},
  author={Christopher D. Manning and M. Eric},
  booktitle={EACL},
  year={2017}
}
  • Christopher D. Manning, M. Eric
  • Published in EACL 2017
  • Computer Science
  • Task-oriented dialogue focuses on conversational agents that participate in user-initiated dialogues on domain-specific topics. In contrast to chatbots, which simply seek to sustain open-ended meaningful discourse, existing task-oriented agents usually explicitly model user intent and belief states. This paper examines bypassing such an explicit representation by depending on a latent neural embedding of state and learning selective attention to dialogue history together with copying to… CONTINUE READING

    Figures, Tables, and Topics from this paper.

    Explore Further: Topics Discussed in This Paper

    Key-Value Retrieval Networks for Task-Oriented Dialogue
    • 168
    • PDF
    Deep Reinforcement Learning: An Overview
    • 417
    • PDF
    Sequicity: Simplifying Task-oriented Dialogue Systems with Single Sequence-to-Sequence Architectures
    • 102
    • Highly Influenced
    • PDF
    Mem2Seq: Effectively Incorporating Knowledge Bases into End-to-End Task-Oriented Dialog Systems
    • 113
    • Highly Influenced
    • PDF
    Global-to-local Memory Pointer Networks for Task-Oriented Dialogue
    • 41
    • PDF
    An End-to-End Trainable Neural Network Model with Belief Tracking for Task-Oriented Dialog
    • 55
    • PDF
    An End-to-end Approach for Handling Unknown Slot Values in Dialogue State Tracking
    • 55
    • PDF

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 34 REFERENCES
    Sequence to Sequence Learning with Neural Networks
    • 10,514
    • PDF
    Long Short-Term Memory
    • 30,932
    • PDF
    Adam: A Method for Stochastic Optimization
    • 49,659
    • PDF
    Neural Machine Translation by Jointly Learning to Align and Translate
    • 12,869
    • Highly Influential
    • PDF
    Effective Approaches to Attention-based Neural Machine Translation
    • 3,918
    • PDF
    A Network-based End-to-End Trainable Task-oriented Dialogue System
    • 569
    • PDF
    Bleu: a Method for Automatic Evaluation of Machine Translation
    • 12,026
    • PDF
    Learning End-to-End Goal-Oriented Dialog
    • 502
    • PDF
    End-To-End Memory Networks
    • 1,491
    • Highly Influential
    • PDF