Papers › Positive Text Reframing under Multi-strategy Optimization

Positive Text Reframing under Multi-strategy Optimization

25 Jul 2024arXiv:2407.17940archive 2025-07-28

Shutong Jia, Biwei Cao, Qingqing Gao, Jiuxin Cao, Bo Liu

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.

PaperPDFCode

Code

20174376/code-for-paper officialmentioned in paperpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Re-RankingText Generationtext similarity

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

AdafactorAdamAttentionAttention DropoutBARTBPEDense ConnectionsDropoutGated Linear UnitInverse Square Root ScheduleLSTMLayer NormalizationLinear LayerMulti-Head AttentionResidual ConnectionSentencePieceSeq2SeqSigmoid ActivationSoftmaxT5Tanh Activation

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections