A Framework for Processing Corrections in Task-Oriented Dialogues

Abstract

Mundane discourse abounds with utterances referring to other utterances. These meta-language utterances appear with surprising frequency in task-oriented dialogues, such as those arising in the context of a natural language interface to an operating system. This paper identifies some simpler types of dialogue-level metalanguage utterance and provides a computational framework to process such phrases in the context of a case-frame parser exploiting strongly-typed domain semantics.

Cite

Text

Hayes and Carbonell. "A Framework for Processing Corrections in Task-Oriented Dialogues." International Joint Conference on Artificial Intelligence, 1983.

Markdown

[Hayes and Carbonell. "A Framework for Processing Corrections in Task-Oriented Dialogues." International Joint Conference on Artificial Intelligence, 1983.](https://mlanthology.org/ijcai/1983/hayes1983ijcai-framework/)

BibTeX

@inproceedings{hayes1983ijcai-framework,
  title     = {{A Framework for Processing Corrections in Task-Oriented Dialogues}},
  author    = {Hayes, Philip J. and Carbonell, Jaime G.},
  booktitle = {International Joint Conference on Artificial Intelligence},
  year      = {1983},
  pages     = {668-670},
  url       = {https://mlanthology.org/ijcai/1983/hayes1983ijcai-framework/}
}