Topic Spotting using Hierarchical Networks with Self Attention

@inproceedings{Chitkara2019TopicSU,
  title={Topic Spotting using Hierarchical Networks with Self Attention},
  author={Pooja Chitkara and Ashutosh Modi and Pravalika Avvaru and Sepehr Janghorbani and Mubbasir Kapadia},
  booktitle={NAACL-HLT},
  year={2019}
}
  • Pooja Chitkara, Ashutosh Modi, +2 authors Mubbasir Kapadia
  • Published in NAACL-HLT 2019
  • Computer Science
  • Success of deep learning techniques have renewed the interest in development of dialogue systems. However, current systems struggle to have consistent long term conversations with the users and fail to build rapport. Topic spotting, the task of automatically inferring the topic of a conversation, has been shown to be helpful in making a dialog system more engaging and efficient. We propose a hierarchical model with self attention for topic spotting. Experiments on the Switchboard corpus show… CONTINUE READING
    3
    Twitter Mentions

    Figures, Tables, and Topics from this paper.

    Citations

    Publications citing this paper.

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 31 REFERENCES

    Hierarchical Attention Networks for Document Classification

    VIEW 6 EXCERPTS
    HIGHLY INFLUENTIAL

    Topic identification from audio recordings using word and phone recognition lattices

    VIEW 4 EXCERPTS
    HIGHLY INFLUENTIAL

    Adam: A Method for Stochastic Optimization

    VIEW 1 EXCERPT

    Transitionbased dependency parsing with stack long shortterm memory

    • Chris Dyer, Miguel Ballesteros, Wang Ling, Austin Matthews, Noah A Smith.
    • arXiv preprint arXiv:1505.08075.
    • 2015
    VIEW 2 EXCERPTS