文献类型：期刊文献

英文题名：Exploiting Duality in Aspect Sentiment Triplet Extraction With Sequential Prompting

作者：Liu, Jingping[1];Chen, Tao[2];Guo, Hao[3];Wang, Chao[4];Jiang, Haiyun[2];Xiao, Yanghua[2];Xu, Xiang[3];Wu, Baohua[3]

机构：[1]East China Univ Sci & Technol, Sch Informat Sci & Engn, Shanghai 200237, Peoples R China;[2]Fudan Univ, Sch Comp Sci, Shanghai 200433, Peoples R China;[3]Alibaba Grp, Hangzhou 311121, Peoples R China;[4]Shanghai Univ, Sch Future Technol, Shanghai 200444, Peoples R China

年份：2024

卷号：36

期号：11

起止页码：6111

外文期刊名：IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING

收录：;EI(收录号：20241715959778);WOS:【SCI-EXPANDED(收录号:WOS:001336378400117)】；

基金：This work was supported in part by the National Natural Science Foundation of China under Grant 62306112, in part by Shanghai Sailing Program under Grant 23YF1409400, in part by the Shanghai Pilot Program for Basic Research under Grant 22TQ1400100-20, and in part by Alibaba Group through Alibaba Innovative Research Program.

语种：英文

外文关键词：Task analysis; Labeling; Tagging; Data mining; Feature extraction; Reviews; Multitasking; Aspect sentiment triplet extraction; dual learning; sequential prompting

摘要：Aspect sentiment triplet extraction is an important task in natural language processing. Previous work tends to focus on the interaction between the aspect and opinion, while ignoring the positive impact of sentiment on interaction within the triplet. In this paper, we propose a novel aspect sentiment triplet extraction model based on dual learning with sequential prompting. This model is designed as a bidirectional extraction framework that fully takes sentiment polarity into account in the interaction process of aspect and opinion. Besides, we introduce a dual loss as a regularization term for the extraction model to promote better learning in both directions. We further design a sequential prompting strategy to determine aspect, opinion, and sentiment polarity more accurately, which utilizes the results extracted in the previous step as prior knowledge to guide the prediction of the next target. We conduct experiments on three public datasets and the results show the effectiveness of our method. More importantly, we deploy our method on Fliggy application and the 14-day online A/B testing indicates that Page View Click-Through Rate and Page View Conversion Rate increase by 1.17% and 1.08% when user short reviews are used for tagging items with the help of our method.