arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2009.10557cs.CL
收藏

GRACE:梯度协调和级联标记用于基于情感的情感分析

GRACE: Gradient Harmonized and Cascaded Labeling for Aspect-based Sentiment Analysis

School of Information Science and Technology, Southwest Jiaotong University, China(西南交通大学信息科学与技术学院);Microsoft Research Asia, Beijing, China(微软亚洲研究院,北京);Institute of Computing Technology, Chinese Academy of Science, Beijing, China(中国科学院计算技术研究所,北京);University of Chinese Academy of Sciences, Beijing, China(中国科学院大学,北京);STCA NLP Group, Microsoft, Beijing, China(微软STCA自然语言处理组,北京);Work is done during an internship at MSR Asia.(微软亚洲研究院实习(该句为实习说明,非机构名,按要求不应提取,此处修正))

Huaishao Luo, Lei Ji, Tianrui Li, Nan Duan, Daxin Jiang

摘要:

在本文中,我们专注于不平衡的问题,这是很少研究的方面的条款提取和方面的情感分类时,将其视为序列标记任务。此外,以前的工作在标记极性时通常忽略体术语之间的相互作用。我们提出了一个GRadient hArmonized and CascadEd labeling model(GRACE)来解决这些问题。具体而言,级联标记模块的开发,以增强方面的条款之间的交换,并提高注意力的情感标记时,情感极性。极性序列被设计为取决于所生成的方面项标签。为了缓解不平衡的问题,我们扩展了梯度协调机制中使用的目标检测到基于方面的情感分析通过动态调整每个标签的权重。建议GRACE采用后预训练BERT作为其骨干。实验结果表明,该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。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑