In this paper, we focus on the imbalance issue, which is rarely studied in aspect term extraction and aspect sentiment classification when regarding them as sequence labeling tasks. Besides, previous works usually ignore the interaction between aspect terms when labeling polarities. We propose a GRadient hArmonized and CascadEd labeling model (GRACE) to solve these problems. Specifically, a cascaded labeling module is developed to enhance the interchange between aspect terms and improve the attention of sentiment tokens when labeling sentiment polarities. The polarities sequence is designed to depend on the generated aspect terms labels. To alleviate the imbalance issue, we extend the gradient harmonized mechanism used in object detection to the aspect-based sentiment analysis by adjusting the weight of each label dynamically. The proposed GRACE adopts a post-pretraining BERT as its backbone. Experimental results demonstrate that the proposed model achieves consistency improvement on multiple benchmark datasets and generates state-of-the-art results.

中文翻译：

---

GRACE：用于基于方面的情感分析的梯度协调和级联标记

在本文中，我们关注不平衡问题，当将它们视为序列标记任务时，很少在方面术语提取和方面情感分类中研究它们。此外，以前的工作在标记极性时通常会忽略方面术语之间的相互作用。我们提出了一个 GRadient hArmonized 和 CascadEd 标签模型（GRACE）来解决这些问题。具体而言，开发了级联标记模块以增强方面术语之间的互换，并在标记情感极性时提高情感标记的注意力。极性序列被设计为取决于生成的方面术语标签。为了缓解不平衡问题，我们通过动态调整每个标签的权重，将对象检测中使用的梯度协调机制扩展到基于方面的情感分析。提议的 GRACE 采用后预训练 BERT 作为其主干。实验结果表明，所提出的模型在多个基准数据集上实现了一致性改进，并产生了最先进的结果。