Back to the Future for Dialogue Research

Abstract

This “blue sky” paper argues that future conversational systems that can engage in multiparty, collaborative dialogues will require a more fundamental approach than existing technology. This paper identifies significant limitations of the state of the art, and argues that our returning to the plan-based approach to dialogue will provide a stronger foundation. Finally, I suggest a research strategy that couples neural network-based semantic parsing with plan-based reasoning in order to build a collaborative dialogue manager.

Cite

Text

Cohen. "Back to the Future for Dialogue Research." AAAI Conference on Artificial Intelligence, 2020. doi:10.1609/AAAI.V34I09.7073

Markdown

[Cohen. "Back to the Future for Dialogue Research." AAAI Conference on Artificial Intelligence, 2020.](https://mlanthology.org/aaai/2020/cohen2020aaai-back/) doi:10.1609/AAAI.V34I09.7073

BibTeX

@inproceedings{cohen2020aaai-back,
  title     = {{Back to the Future for Dialogue Research}},
  author    = {Cohen, Philip R.},
  booktitle = {AAAI Conference on Artificial Intelligence},
  year      = {2020},
  pages     = {13514-13519},
  doi       = {10.1609/AAAI.V34I09.7073},
  url       = {https://mlanthology.org/aaai/2020/cohen2020aaai-back/}
}