A Knowledge-Enhanced Adversarial Model for Cross-lingual Structured Sentiment Analysis

doi:10.1109/IJCNN55064.2022.9892801

	A Knowledge-Enhanced Adversarial Model for Cross-lingual Structured Sentiment Analysis
	Zhang, Qi 1; Zhou, Jie 2; Chen, Qin 1; Bai, Qingchun 3; Xiao, Jun 3; He, Liang 1
	2022
会议名称	IEEE International Conference on Fuzzy Systems (FUZZ-IEEE) / IEEE World Congress on Computational Intelligence (IEEE WCCI) / International Joint Conference on Neural Networks (IJCNN) / IEEE Congress on Evolutionary Computation (IEEE CEC)
会议录名称	IEEE
会议日期	JUL 18-23, 2022
会议地点	Padua, ITALY
出版地	NEW YORK
摘要	Structured sentiment analysis, which aims to extract the complex semantic structures such as holders, expressions, targets, and polarities, has obtained widespread attention from both industry and academia. Unfortunately, the existing structured sentiment analysis datasets refer to a few languages and are relatively small, limiting neural network models' performance. In this paper, we focus on the cross-lingual structured sentiment analysis task, which aims to transfer the knowledge from the source language to the target one. Notably, we propose a Knowledge-Enhanced Adversarial Model (KEAM) with both implicit distributed and explicit structural knowledge to enhance the cross-lingual transfer. First, we design an adversarial embedding adapter for learning an informative and robust representation by capturing implicit semantic information from diverse multi-lingual embeddings adaptively. Then, we propose a syntax GCN encoder to transfer the explicit semantic information (e.g., universal dependency tree) among multiple languages. We conduct experiments on five datasets and compare KEAM with both the supervised and unsupervised methods. The extensive experimental results show that our KEAM model outperforms all the unsupervised baselines in various metrics.
关键词	cross-lingual structured sentiment analysis adversarial knowledge
DOI	10.1109/IJCNN55064.2022.9892801
收录类别	CPCI-S
语种	英语
WOS研究方向	Computer Science ; Engineering ; Neurosciences & Neurology
WOS类目	Computer Science, Artificial Intelligence ; Computer Science, Hardware & Architecture ; Engineering, Electrical & Electronic ; Neurosciences
WOS记录号	WOS:000867070907038
原始文献类型	Proceedings Paper
引用统计	被引频次[WOS]：0 [WOS记录] [WOS相关记录]
文献类型	会议论文
条目标识符	http://ir.library.ouchn.edu.cn/handle/39V7QQFX/168842
专题	国家开放大学上海分部
通讯作者	Zhou, Jie
作者单位	1.East China Normal Univ, Sch Comp Sci & Technol, Shanghai, Peoples R China; 2.Fudan Univ, Sch Comp Sci, Shanghai, Peoples R China; 3.Shanghai Open Univ, Shanghai, Peoples R China
推荐引用方式 GB/T 7714	Zhang, Qi,Zhou, Jie,Chen, Qin,et al. A Knowledge-Enhanced Adversarial Model for Cross-lingual Structured Sentiment Analysis[C]. NEW YORK,2022.