Dealing with Trouble: A Data-Driven Model of a Repair Type for a Conversational Agent

Abstract

Troubles in hearing, comprehension or speech production are common in human conversations, especially if participants of the conversation communicate in a foreign language that they have not yet fully mastered. Here I describe a data-driven model for simulation of dialogue sequences where the learner user does not understand the talk of a conversational agent in chat and asks for clarification.

Cite

Text

Höhn. "Dealing with Trouble: A Data-Driven Model of a Repair Type for a Conversational Agent." AAAI Conference on Artificial Intelligence, 2015. doi:10.1609/AAAI.V29I1.9724

Markdown

[Höhn. "Dealing with Trouble: A Data-Driven Model of a Repair Type for a Conversational Agent." AAAI Conference on Artificial Intelligence, 2015.](https://mlanthology.org/aaai/2015/hohn2015aaai-dealing/) doi:10.1609/AAAI.V29I1.9724

BibTeX

@inproceedings{hohn2015aaai-dealing,
  title     = {{Dealing with Trouble: A Data-Driven Model of a Repair Type for a Conversational Agent}},
  author    = {Höhn, Sviatlana},
  booktitle = {AAAI Conference on Artificial Intelligence},
  year      = {2015},
  pages     = {4166-4167},
  doi       = {10.1609/AAAI.V29I1.9724},
  url       = {https://mlanthology.org/aaai/2015/hohn2015aaai-dealing/}
}