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:
- 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)
- PDF:
- https://preview.aclanthology.org/paclic-22-ingestion/2022.findings-emnlp.355.pdf