福州大学学报（自然科学版）2024，Vol.52Issue(4)：413-420,8.DOI:10.7631/issn.1000-2243.23370
从整体到局部优化的文本风格迁移模型
A text style transfer model from global to local optimization
摘要
Abstract
A global-local based style transfer(G-LST)framework is proposed,optimizing from a glob-al to a local level.Firstly,extensive source-side data is used for iterative optimization to automatically construct high-quality pseudo-parallel data,and through joint training to improve the model's seman-tic perception of the global style.Subsequently,the model enhances the local style representation by modifying the style at the word level with commonsense knowledge.This method considers both global and local styles simultaneously,thereby improving the accuracy of style transfer.Experimental results on the GYAFC dataset show that compared with the state-of-the-art text style transfer model,the G-LST model's style transfer accuracy on data in the E&M and F&R fields has increased by 2.70%and 4.47%respectively.The comprehensive metrics for content preservation and style accuracy have improved by 1.18%and 1.95%respectively.关键词
文本风格迁移/迭代优化/联合训练/常识性知识Key words
text style transfer/iterative optimization/joint training/commonsense knowledge分类
信息技术与安全科学引用本文复制引用
范剑宏,杨州,蔡铁城,吴运兵,廖祥文..从整体到局部优化的文本风格迁移模型[J].福州大学学报（自然科学版）,2024,52(4):413-420,8.基金项目
国家自然科学基金资助项目(61976054) （61976054）
