He Said, She Said: Style Transfer for Shifting the Perspective of Dialogues

Amanda Bertsch, Graham Neubig, Matthew R. Gormley


Abstract
In this work, we define a new style transfer task: perspective shift, which reframes a dialouge from informal first person to a formal third person rephrasing of the text. This task requires challenging coreference resolution, emotion attribution, and interpretation of informal text. We explore several baseline approaches and discuss further directions on this task when applied to short dialogues. As a sample application, we demonstrate that applying perspective shifting to a dialogue summarization dataset (SAMSum) substantially improves the zero-shot performance of extractive news summarization models on this data. Additionally, supervised extractive models perform better when trained on perspective shifted data than on the original dialogues. We release our code publicly.
Anthology ID:
2022.findings-emnlp.355
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2022
Month:
December
Year:
2022
Address:
Abu Dhabi, United Arab Emirates
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
4823–4840
Language:
URL:
https://aclanthology.org/2022.findings-emnlp.355
DOI:
Bibkey:
Cite (ACL):
Amanda Bertsch, Graham Neubig, and Matthew R. Gormley. 2022. He Said, She Said: Style Transfer for Shifting the Perspective of Dialogues. In Findings of the Association for Computational Linguistics: EMNLP 2022, pages 4823–4840, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.
Cite (Informal):
He Said, She Said: Style Transfer for Shifting the Perspective of Dialogues (Bertsch et al., Findings 2022)
Copy Citation:
PDF:
https://preview.aclanthology.org/paclic-22-ingestion/2022.findings-emnlp.355.pdf