基于注意力网络的情感分析中的对比句处理

方面级情感分析旨在确定评论中对特定方面的情绪极性，但目前较少研究复杂句对情感分类的影响。基于此，提出了一种基于BERT和带相对位置自注意力网络的方面级情感分析模型。首先，通过动态加权采样方法平衡对比句稀缺的问题，使模型学习到更多的对比句特征信息；其次，利用双头自注意力网络提取带相对位置的特征表示，与预训练模型得到的带绝对位置的特征表示联合训练；最后，通过标签平衡技术对模型正则化处理，稳定模型对中性样本的辨识。该模型在SemEval 2014 Task 4 Sub Task 2上进行实验，在两个数据集上的accuracy和macro-F1指标都有所提高。实验结果表明该模型在对比句分类上是有效的，同时在整个测试集上分类也优于其他基准模型。

Handling contrastive sentences in sentiment analysis based on attention network

Aspect-level sentiment analysis aims to determine the sentiment polarity towards specific aspect in reviews. However, little research has been done on the influence of complex sentences on sentiment classification. Based on this, this paper proposed an aspect sentiment classification model based on BERT and self-attention network with relative position. Firstly, it used the dynamic weighted sampling method to balance the rare contrastive sentences, so that the model could learn more contrastive sentence feature information. Then, it jointly trained the feature representations extracted by double-head self-attention network with relative position and the feature representations obtained by the Pre-trained model with absolute position. Finally, it used the label smoothing regularization technology to stabilize the model to identify the neutral samples. This paper tested this model on Sub Task 2 in SemEval 2014 task, and improved both accuracy and macro-F1 indicators of the two datasets. The experimental results show that the effectiveness of the proposed model for contrastive sentences classification, and also yield improvements in the whole test set over other benchmark models.