Dialog context language modeling with recurrent neural networks

@article{Liu2017DialogCL,
  title={Dialog context language modeling with recurrent neural networks},
  author={Bing Liu and Ian Lane},
  journal={2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
  year={2017},
  pages={5715-5719}
}
In this work, we propose contextual language models that incorporate dialog level discourse information into language modeling. Previous works on contextual language model treat preceding utterances as a sequence of inputs, without considering dialog interactions. We design recurrent neural network (RNN) based contextual language models that specially track the interactions between speakers in a dialog. Experiment results on Switchboard Dialog Act Corpus show that the proposed model outperforms… CONTINUE READING
6
Twitter Mentions

Figures, Tables, Results, and Topics from this paper.

Key Quantitative Results

  • Experiment results on Switchboard Dialog Act Corpus show that the proposed model outperforms conventional single turn based RNN language model by 3.3% on perplexity.
  • Our evaluation results on Switchboard Dialog Act Corpus show that the proposed model outperform conventional RNN language model by 3.3%.

Citations

Publications citing this paper.
SHOWING 1-10 OF 12 CITATIONS

Multiple-Weight Recurrent Neural Networks

VIEW 5 EXCERPTS
CITES METHODS
HIGHLY INFLUENCED

Large Context End-to-end Automatic Speech Recognition via Extension of Hierarchical Recurrent Encoder-decoder Models

  • ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
  • 2019

A Conversational Neural Language Model for Speech Recognition in Digital Assistants

  • 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
  • 2018
VIEW 1 EXCERPT
CITES BACKGROUND

Dialog-Context Aware end-to-end Speech Recognition

  • 2018 IEEE Spoken Language Technology Workshop (SLT)
  • 2018
VIEW 1 EXCERPT
CITES METHODS

Neural Dialogue Context Online End-of-Turn Detection

  • SIGDIAL Conference
  • 2018
VIEW 1 EXCERPT
CITES BACKGROUND

References

Publications referenced by this paper.
SHOWING 1-10 OF 19 REFERENCES

Similar Papers

Loading similar papers…