Inducing Positive Perspectives with Text Reframing
This addresses the problem of generating positive text perspectives without altering meaning for applications in psychology and NLP, but it is incremental as it builds on existing text style transfer tasks.
The paper tackled the task of positive reframing, which neutralizes negative viewpoints to generate positive perspectives while preserving original meaning, and introduced a large-scale benchmark with 8,349 sentence pairs and 12,755 annotations to evaluate state-of-the-art models.
Sentiment transfer is one popular example of a text style transfer task, where the goal is to reverse the sentiment polarity of a text. With a sentiment reversal comes also a reversal in meaning. We introduce a different but related task called positive reframing in which we neutralize a negative point of view and generate a more positive perspective for the author without contradicting the original meaning. Our insistence on meaning preservation makes positive reframing a challenging and semantically rich task. To facilitate rapid progress, we introduce a large-scale benchmark, Positive Psychology Frames, with 8,349 sentence pairs and 12,755 structured annotations to explain positive reframing in terms of six theoretically-motivated reframing strategies. Then we evaluate a set of state-of-the-art text style transfer models, and conclude by discussing key challenges and directions for future work.