基于课程学习的跨度级方面情感三元组提取  

Span-level aspect sentiment triplet extraction based on curriculum learning

作　　者：侯明泽 饶蕾[1] 范光宇[1] 陈年生[1] 程松林 HOU Mingze;RAO Lei;FAN Guangyu;CHEN Niansheng;CHENG Songlin(School of Electronic Information Engineering Shanghai Dianji University,Shanghai 201306,China)

机构地区：[1]上海电机学院电子信息学院,上海201306

出　　处：《浙江大学学报(工学版)》2025年第1期79-88,共10页Journal of Zhejiang University:Engineering Science

基　　金：国家自然科学基金资助项目(61702320).

摘　　要：现有方面情感三元组提取方法存在无法充分利用预训练模型知识,容易出现过拟合或欠拟合,识别语句细粒度方面词和情感极性的能力不足等问题,为此提出基于课程学习框架的跨度级方面情感三元组提取方法.该方法基于课程学习框架进行数据预处理,使用预训练模型学习句子的上下文表示,搭建跨度模型提取句子中所有可能的跨度,基于双通道提取方面词和意见词,筛出正确的方面词和意见词组合进行情感分类.在ASTEData-V2数据集上的实验结果表明,所提方法的F1值比SPAN-ASTE的F1值提升了2个百分点,所提方法的实验结果优于GTS、B-MRC、JET等其他方面情感三元组提取方法.Exiting methods of aspect sentiment triplet extraction suffer from the problems of not being able to fully utilize the knowledge of the pre-trained model,being prone to overfitting or underfitting,and having insufficient ability to recognize the fine-grained aspects and sentiments of an utterance.A method for extracting span-level aspect sentiment triples based on a curriculum learning framework was proposed.Data preprocessing was performed based on the curriculum learning framework,and the contextual representation of a sentence was learned using a pretrained model.By building a span model,all possible spans were extracted in a sentence.Aspect and opinion terms were extracted based on the dual channel,and the correct combinations of aspect-opinion were filtered out for sentiment categorization.Experimental results on the ASTE-Data-V2 dataset show that the F1 value of the proposed method is improved by 2 percentage points over that of SPAN-ASTE.The experimental results of the proposed method outperform the other aspect sentiment triplet extraction methods such as GTS,B-MRC,and JET.

关 键 词：课程学习 跨度模型 方面情感三元组提取 双通道 情感分类 

分 类 号：TP391.1[自动化与计算机技术—计算机应用技术]