From rule-based to data-driven lexical entrainment models in spoken dialog systems

@article{Lopes2015FromRT,
  title={From rule-based to data-driven lexical entrainment models in spoken dialog systems},
  author={Jos{\'e} Lopes and Maxine Esk{\'e}nazi and Isabel Trancoso},
  journal={Comput. Speech Lang.},
  year={2015},
  volume={31},
  pages={87-112}
}
  • José Lopes, Maxine Eskénazi, Isabel Trancoso
  • Published in Comput. Speech Lang. 2015
  • Computer Science
  • HighlightsNew methods for the integration of lexical entrainment in spoken dialog systems.Rule based method for entrainment implemented in two different systems.Data-driven method for lexical entrainment in SDSs.Tests reveal better performance with entrainment policy. This paper presents uses a data-driven approach to improve Spoken Dialog System (SDS) performance by automatically finding the most appropriate terms to be used in system prompts. The literature shows that speakers use one another… CONTINUE READING

    Create an AI-powered research feed to stay up to date with new papers like this posted to ArXiv

    Citations

    Publications citing this paper.
    SHOWING 1-9 OF 9 CITATIONS

    Exploring Interaction with Remote Autonomous Systems using Conversational Agents

    VIEW 1 EXCERPT
    CITES BACKGROUND

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 29 REFERENCES

    Towards choosing better primes for spoken dialog systems

    Broadcast news subtitling system in Portuguese