EMNLP 2023long findings0 citations

Conditioning on Dialog Acts improves Empathy Style Transfer

Renyi Qu, Lyle Ungar, João Sedoc

Abstract

We explore the role of dialog acts in style transfer, specifically empathy style transfer -- rewriting a sentence to make it more empathetic without changing its meaning. Specifically, we use two novel few-shot prompting strategies: target prompting, which only uses examples of the target style (unlike traditional prompting with source/target pairs), and dialog-act-conditioned prompting, which first estimates the dialog act of the source sentence and then makes it more empathetic using few-shot examples of the same dialog act. Our study yields two key findings: (1) Target prompting typically improves empathy more effectively while maintaining the same level of semantic similarity; (2) Dialog acts matter. Dialog-act-conditioned prompting enhances empathy while preserving both semantics and the dialog-act type. Different dialog acts benefit differently from different prompting methods, highlighting the need for further investigation of the role of dialog acts in style transfer.

empathy style transfertext style transferempathyGPT-4large language modelsdialog actspragmaticsprompt engineeringin-context learningfew-shot prompting
BibTeX
@inproceedings{
qu2023conditioning,
title={Conditioning on Dialog Acts improves Empathy Style Transfer},
author={Renyi Qu and Lyle Ungar and Jo{\~a}o Sedoc},
booktitle={The 2023 Conference on Empirical Methods in Natural Language Processing},
year={2023},
url={https://openreview.net/forum?id=AQiuwWLvim}
}
Conditioning on Dialog Acts improves Empathy Style Transfer · EMNLP 2023