摘要
细粒度的情感分类任务需要识别文本当中与评论对象相关度最高的观点词并进行情感极性分类.文中利用多头注意力机制改进记忆网络,提取不同对象情感分类特征,实现对象级情感分类.将文本的词嵌入向量存储在记忆组件中,使用多头注意力机制在多个特征空间同时建模文本整体语义与对象相关语义.利用前馈网络层整合多个特征空间下的信息作为分类特征.在SemEval-2014数据集及扩充的数据集上实验表明,文中方法有利于缓解方法的选择性偏好.
A fine-grained sentiment classification task is to identify the opinion words with the highest degree of correlation with target words and classify the emotional polarity in the text.A deep memory network with multiple-head attention mechanism for aspect level sentiment classification is introduced.The word embedding vector of the text is stored in the memory component,and the multi-head attention mechanism is employed to simultaneously model the overall semantics of the text and the object-related semantics among the multiple feature spaces.A feedforward network layer is applied to integrate the information in multiple feature spaces as a classification feature.Experiments on SemEval-2014 dataset and the extended dataset show that the proposed method is beneficial to alleviate the selective preference of the model.
作者
张新生
高腾
ZHANG Xingsheng;GAO Teng(School of Management,Xi′an University of Architecture and Technology,Xi′an 710055)
出处
《模式识别与人工智能》
EI
CSCD
北大核心
2019年第11期997-1005,共9页
Pattern Recognition and Artificial Intelligence
基金
国家自然科学基金项目(No.4187752)资助~~
关键词
文本情感分类
细粒度情感分析
注意力机制
记忆神经网络
Text Sentiment Classification
Fine-Grained Sentiment Analysis
Attention Mechanism
Memory Neural Network
