Word-Based Dialog State Tracking with Recurrent Neural Networks

@inproceedings{Henderson2014WordBasedDS,
  title={Word-Based Dialog State Tracking with Recurrent Neural Networks},
  author={Matthew Henderson and B. Thomson and S. Young},
  booktitle={SIGDIAL Conference},
  year={2014}
}
  • Matthew Henderson, B. Thomson, S. Young
  • Published in SIGDIAL Conference 2014
  • Computer Science
  • Recently discriminative methods for tracking the state of a spoken dialog have been shown to outperform traditional generative models. This paper presents a new wordbased tracking method which maps directly from the speech recognition results to the dialog state without using an explicit semantic decoder. The method is based on a recurrent neural network structure which is capable of generalising to unseen dialog state hypotheses, and which requires very little feature engineering. The method… CONTINUE READING
    Encoding Word Confusion Networks with Recurrent Neural Networks for Dialog State Tracking
    8
    Incremental LSTM-based dialog state tracker
    43
    Dialog History Construction with Long-Short Term Memory for Robust Generative Dialog State Tracking
    9
    Machine Learning for Dialog State Tracking: A Review
    57
    Dialog state tracking using long short-term memory neural networks
    7
    Dialog state tracking, a machine reading approach using a memory-enhanced neural network
    2

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 16 REFERENCES
    Recipe For Building Robust Spoken Dialog State Trackers: Dialog State Tracking Challenge System Description
    58
    Multi-domain learning and generalization in dialog state tracking
    40
    Structured Discriminative Model For Dialog State Tracking
    51
    Discriminative spoken language understanding using word confusion networks
    84
    The Second Dialog State Tracking Challenge
    318
    Semantic parsing using word confusion networks with conditional random fields
    39
    Dialog State Tracking using Conditional Random Fields
    28
    A “K Hypotheses + Other” Belief Updating Model
    70