AOA-BERT:一种基于对抗学习的方面级情感分类方法

AOA-BERT:a Aspect-level Sentiment Classification Method Based on Adversarial Learning

方面级情感分类是一种细粒度的情感分析任务,旨在分析出文本不同方面的情感.针对方面级情感分类模型存在分类精度低、泛化性弱等问题,提出基于对抗学习的AOA-BERT方面级情感分类模型(Attention-Over-Attention-BERT for aspect-level sentiment classification model based on adversarial learning,AOA-BERT).首先,将文本和方面词单独建模,通过BERT编码提取隐含层特征.其次,将隐含层特征放入AOA(Attention-Over-Attention)网络提取权重向量.最后,将权重向量与建模后的文本特征向量相乘,并做交叉熵损失、回传参数.此外,通过对抗学习算法生成和学习对抗样本,作为一种文本数据增强方法,优化决策边界.实验结果表明,和大多数深度神经网络情感分类模型相比,AOA-BERT能提升情感分类的准确性.同时,通过消融实验,证明了AOA-BERT结构设计的合理性.

Aspect-level sentiment classification is a fine-grained sentiment analysis task that aims to analyze the sentiment of different aspects of a text.To address the problems of low classification accuracy and weak generalization of aspect-level sentiment classification models,Attention-Over-Attention-BERT for aspect-level sentiment classification model based on adversarial learning is proposed.Firstly,the text and aspect words are modeled separately,and the hidden layer features are extracted by BERT coding.secondly,the hidden layer features are put into AOA network to extract weight vector.Finally,the weight vector is multiplied with the modeled text feature vector,and cross-entropy loss,back-propagation parameters are done.In addition,adversarial samples are generated and learned by adversarial learning algorithms as a textual data enhancement method to optimize decision boundaries.The experimental results show that,compared with most deep neural network sentiment classification models,AOA-BERT can improve the accuracy of sentiments classification.Meanwhile,the ablation experiment proves that the structural design of AOA-BERT is reasonable.