基于生成提示的无监督文本情感转换方法  

Unsupervised text sentiment transfer method based on generation prompt

作　　者：黄于欣 徐佳龙 余正涛[1,2] 侯书楷 周家啟 HUANG Yuxin;XU Jialong;YU Zhengtao;HOU Shukai;ZHOU Jiaqi(Faculty of Information Engineering and Automation,Kunming University of Science and Technology,Kunming Yunnan 650500,China;Key Laboratory of Artificial Intelligence in Yunnan Province(Kunming University of Science and Technology),Kunming Yunnan 650500,China)

机构地区：[1]昆明理工大学信息工程与自动化学院,昆明650500 [2]云南省人工智能重点实验室(昆明理工大学),昆明650500

出　　处：《计算机应用》2024年第9期2667-2673,共7页journal of Computer Applications

基　　金：国家自然科学基金资助项目(U21B2027,62266027,62266028,61972186);云南省基础研究项目(202301AT070471,202201AS070179);云南省重大科技专项(202302AD080003);昆明理工大学“双一流”创建联合专项(202201BE070001-021)。

摘　　要：文本情感转换是在保留内容的基础上更改文本的情感属性。由于缺乏平行语料,现有无监督文本情感转换的方法主要通过文本重建和分类损失来构建情感和内容的潜在表征,实现情感转换。然而,这种弱监督信号训练策略在提示学习范式下的模型性能退化严重。针对以上问题,提出一种基于生成提示的无监督文本情感转换方法。首先,通过提示生成器生成文本内容提示;其次,融合目标情感提示作为最终提示;最后,构建两阶段的训练策略,为模型训练提供平滑的训练梯度以解决模型性能退化的问题。在情感转换的公共数据集Yelp上的实验结果表明,所提方法的文本保留度、情感转换分数和BLEU(BiLingual Evaluation Understudy)显著优于基于生成的方法UnpairedRL,分别提高了39.1%、62.3%和14.5%。Text sentiment transfer is to change text’s sentiment attribute while preserving its content.Due to the lack of parallel corpora,most of the existing unsupervised methods for text sentiment transfer construct latent representations of sentiment and content through text reconstruction and classification losses,and then realize sentiment transfer.However,this weakly supervised training strategy results in significant model performance degradation under prompt learning paradigms.To address this issue,an unsupervised text sentiment transfer method based on generation prompt was proposed.Firstly,textual content prompts were generated by using a prompt generator.Secondly,the target sentiment prompts were fused as the ultimate prompt.Finally,a two-stage training strategy was formulated to provide smooth training gradients for the model training,thereby solving the problem of model performance degradation.Experimental results on the public dataset for sentiment transfer—Yelp show that the proposed method significantly outperforms the generation based method UnpairedRL in text preservation,sentiment transfer score,and BLEU(BiLingual Evaluation Understudy),and the improvements are 39.1%,62.3%,and 14.5%,respectively.

关 键 词：无监督 情感转换 内容生成提示 文本重建 情感分类 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]