Share this page:

DiSCoL: Toward Engaging Dialogue Systems through Conversational Line Guided Response Generation

Sarik Ghazarian, Zixi Liu, Tuhin Chakrabarty, Xuezhe Ma, Aram Galstyan, and Nanyun Peng, 2021 Annual Conference of the North American Chapter of the Association for Computational Linguistics (NAACL 2021), Demonstrations Track, 2021.

Download the full text


Abstract

Having engaging and informative conversations with users is the utmost goal for open-domain conversational systems. Recent advances in transformer-based language models and their applications to dialogue systems have succeeded to generate fluent and human-like responses. However, they still lack control over the generation process towards producing contentful responses and achieving engaging conversations. To achieve this goal, we present DiSCoL (Dialogue Systems through Coversational Line guided response generation). DiSCoL is an open-domain dialogue system that leverages conversational lines (briefly convlines) as controllable and informative content-planning elements to guide the generation model produce engaging and informative responses. Two primary modules in DiSCoL’s pipeline are conditional generators trained for 1) predicting relevant and informative convlines for dialogue contexts and 2) generating high-quality responses conditioned on the predicted convlines. Users can also change the returned convlines to control the direction of the conversations towards topics that are more interesting for them. Through automatic and human evaluations, we demonstrate the efficiency of the convlines in producing engaging conversations.


Bib Entry

@article{ghazarian2021discol,
  title = {DiSCoL: Toward Engaging Dialogue Systems through Conversational Line Guided Response Generation},
  author = {Ghazarian, Sarik and Liu, Zixi and Chakrabarty, Tuhin and Ma, Xuezhe and Galstyan, Aram and Peng, Nanyun},
  booktitle = {2021 Annual Conference of the North American Chapter of the Association for Computational Linguistics (NAACL 2021), Demonstrations Track},
  year = {2021}
}

Related Publications

  • DiSCoL: Toward Engaging Dialogue Systems through Conversational Line Guided Response Generation

    Sarik Ghazarian, Zixi Liu, Tuhin Chakrabarty, Xuezhe Ma, Aram Galstyan, and Nanyun Peng, 2021 Annual Conference of the North American Chapter of the Association for Computational Linguistics (NAACL 2021), Demonstrations Track, 2021.
    Full Text Code Abstract BibTeX Details
    Having engaging and informative conversations with users is the utmost goal for open-domain conversational systems. Recent advances in transformer-based language models and their applications to dialogue systems have succeeded to generate fluent and human-like responses. However, they still lack control over the generation process towards producing contentful responses and achieving engaging conversations. To achieve this goal, we present DiSCoL (Dialogue Systems through Coversational Line guided response generation). DiSCoL is an open-domain dialogue system that leverages conversational lines (briefly convlines) as controllable and informative content-planning elements to guide the generation model produce engaging and informative responses. Two primary modules in DiSCoL’s pipeline are conditional generators trained for 1) predicting relevant and informative convlines for dialogue contexts and 2) generating high-quality responses conditioned on the predicted convlines. Users can also change the returned convlines to control the direction of the conversations towards topics that are more interesting for them. Through automatic and human evaluations, we demonstrate the efficiency of the convlines in producing engaging conversations.
    @article{ghazarian2021discol,
      title = {DiSCoL: Toward Engaging Dialogue Systems through Conversational Line Guided Response Generation},
      author = {Ghazarian, Sarik and Liu, Zixi and Chakrabarty, Tuhin and Ma, Xuezhe and Galstyan, Aram and Peng, Nanyun},
      booktitle = {2021 Annual Conference of the North American Chapter of the Association for Computational Linguistics (NAACL 2021), Demonstrations Track},
      year = {2021}
    }
    
    Details