He Said, She Said: Style Transfer for Shifting the Perspective of Dialogues
This work addresses a novel style transfer task for dialogue processing, which is incremental as it builds on existing summarization techniques but introduces a specific transformation for informal text.
The paper tackles the problem of perspective shift in dialogues by reframing informal first-person text to formal third-person rephrasing, requiring coreference resolution and emotion attribution. The result shows that applying this shift to the SAMSum dataset improves zero-shot performance of extractive news summarization models and enhances supervised models when trained on the shifted data.
In this work, we define a new style transfer task: perspective shift, which reframes a dialogue 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.