KENAOTE:一种知识增强的方面和意见对提取多任务学习模型  

KENAOTE:multi-task learning model for knowledge augmented aspect and opinion pair extraction

作　　者：李阳 唐积强[3] 朱俊武[1] 梁明轩[1,2] 高翔 Li Yang;Tang Jiqiang;Zhu Junwu;Liang Mingxuan;Gao Xiang(College of Information Engineering,Yangzhou University,Yangzhou Jiangsu 225127,China;Institute of Computing Technology,Chinese Academy of Sciences,Beijing 100190,China;National Computer Network Emergency Response Technical Team/Coordination Center of China,Beijing 100029,China)

机构地区：[1]扬州大学信息工程学院,江苏扬州225127 [2]中国科学院计算技术研究所,北京100190 [3]国家计算机网络应急技术处理协调中心,北京100029

出　　处：《计算机应用研究》2023年第2期359-364,共6页Application Research of Computers

基　　金：国家“242信息安全”计划资助项目(2021A008);北京市科技新星计划交叉学科合作课题(Z191100001119014);国家重点研发计划重点专项资助项目(2017YFC1700300,2017YFB1002300);国家自然科学基金资助项目(61702234);江苏省(扬州大学)研究生科研与实践创新计划资助项目(SJCX21_1551)。

摘　　要：方面和意见对提取旨在根据给定句子提取方面和意见项并匹配关系,然而相关研究通常独立提取方面和意见项,而不识别关系。为了识别方面和意见项关系,提出一种知识增强的方面和意见对提取多任务学习模型。首先使用预训练语言模型为文本生成具有语义信息的词向量,为了实现知识增强的效果,使用遮蔽注意力的方式将知识图谱的语义信息融入词向量中,然后使用基于距离注意力和条件随机场的序列标注方法提取方面和意见项,最后再将提取的方面和意见项两两匹配预测对应关系。为了加强方面和意见项提取模块和匹配模块的联系,采用共享编码层的方式实现联合训练。在训练流程中,匹配模块采用真实标签作为输入,在测试过程中采用提取模块的结果作为输入。为了证明模型的有效性,使用三个通用领域数据集进行对比实验,该模型在方面和意见项匹配任务中F 1值分别达到66.99%、75.17%和67.30%,并优于其他比较模型。Aspect and opinion pair extraction aims to extract aspect and opinion items and match relations from a given sentence.However,related studies typically extract aspects and opinions independently without identifying the relationships.To identify the relationships of aspect and opinion item,this paper proposed a knowledge-augmented multi-task learning model for aspect and opinion pair extraction.First,it used the pre-trained language model to generate word vectors with semantic information for the text.In order to achieve the effect of knowledge enhancement,it used the masked attention mechanism to integrate the semantic information of the knowledge graph into the word vectors,and used the sequence labeling method based on the distance-based attention and conditional random fields to extract aspects and opinions.Finally,it matched the extracted aspects and opinions to predict the corresponding relationship.In order to strengthen the connection between the aspect and opinion extraction module and the matching module,the model adopted a shared coding layer to achieve joint training.In addition,in the training process,the matching module used the real labels as input,and used the result of the extraction module as input in the testing process.Finally,to demonstrate the effectiveness of the model,this paper used three general domain datasets for comparative experiments.The model achieves F 1 values of 66.99%,75.17%and 67.30%in aspect and opinion matching tasks respectively,and outperforms other comparative models.

关 键 词：知识增强 深度学习 方面级情感分析 方面和意见对提取 联合训练 

分 类 号：TP391.1[自动化与计算机技术—计算机应用技术]