Positive Text Reframing under Multi-strategy Optimization
This work addresses the problem of positive text reframing for natural language processing applications, offering an incremental improvement over existing fine-tuning methods.
The paper tackles the challenge of generating fluent, diverse, and task-constrained positive reframing text by proposing a multi-strategy optimization framework (MSOF) that integrates sentiment and content rewards, decoding optimizations, and multi-dimensional re-ranking, achieving significant improvements on unconstrained and controlled tasks with BART and T5 models.
Differing from sentiment transfer, positive reframing seeks to substitute negative perspectives with positive expressions while preserving the original meaning. With the emergence of pre-trained language models (PLMs), it is possible to achieve acceptable results by fine-tuning PLMs. Nevertheless, generating fluent, diverse and task-constrained reframing text remains a significant challenge. To tackle this issue, a \textbf{m}ulti-\textbf{s}trategy \textbf{o}ptimization \textbf{f}ramework (MSOF) is proposed in this paper. Starting from the objective of positive reframing, we first design positive sentiment reward and content preservation reward to encourage the model to transform the negative expressions of the original text while ensuring the integrity and consistency of the semantics. Then, different decoding optimization approaches are introduced to improve the quality of text generation. Finally, based on the modeling formula of positive reframing, we propose a multi-dimensional re-ranking method that further selects candidate sentences from three dimensions: strategy consistency, text similarity and fluency. Extensive experiments on two Seq2Seq PLMs, BART and T5, demonstrate our framework achieves significant improvements on unconstrained and controlled positive reframing tasks.