A weakly supervised knowledge attentive network for aspect-level sentiment classification

doi:10.1007/s11227-022-04820-w

	A weakly supervised knowledge attentive network for aspect-level sentiment classification
	Bai, Qingchun 1,2; Xiao, Jun 1; Zhou, Jie 3
	2023-03
发表期刊	JOURNAL OF SUPERCOMPUTING
ISSN	0920-8542
卷号	79 期号:5 页码:5403-5420
摘要	Deep neural networks have achieved good performance in recent years for aspect-level sentiment classification (ASC), whereas most neural ASC models neglect the commonsense knowledge absent from text but essential for aspect affective understanding, which largely limits the performance of neural ASC. In this paper, we propose a Weakly Supervised Knowledge Attentive Network, which resolves the above problems via knowledge attention and weakly supervised learning. Specifically, we first present a Knowledge Attentive Network (KAN) to capture more aspect-related information by incorporating external commonsense knowledge into the attention mechanism. Then, we propose a weakly supervised learning method, which allows our KAN model to learn more knowledge from the pseudo-samples generated upon the rich-resource document-level sentiment classification datasets. Extensive experiments on four benchmark datasets show the significant advantages of our proposed approach. In particular, we obtain state-of-the-art performance in terms of accuracy on all the datasets.
关键词	Sentiment analysis Knowledge attentive network Aspect-level sentiment analysis
DOI	10.1007/s11227-022-04820-w
收录类别	SCIE
语种	英语
WOS研究方向	Computer Science ; Engineering
WOS类目	Computer Science, Hardware & Architecture ; Computer Science, Theory & Methods ; Engineering, Electrical & Electronic
WOS记录号	WOS:000870950000003
出版者	SPRINGER
原始文献类型	Article ; Early Access
EISSN	1573-0484
引用统计	被引频次：3[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://ir.library.ouchn.edu.cn/handle/39V7QQFX/168621
专题	国家开放大学上海分部
通讯作者	Bai, Qingchun
作者单位	1.Shanghai Open Univ, Shanghai Engn Res Ctr Open Distance Educ, Shanghai, Peoples R China; 2.ECNUP, NPPA Key Lab Publishing Integrat Dev, Shanghai, Peoples R China; 3.Fudan Univ, Shanghai, Peoples R China
第一作者单位	国家开放大学上海分部
通讯作者单位	国家开放大学上海分部
第一作者的第一单位	国家开放大学上海分部
推荐引用方式 GB/T 7714	Bai, Qingchun,Xiao, Jun,Zhou, Jie. A weakly supervised knowledge attentive network for aspect-level sentiment classification[J]. JOURNAL OF SUPERCOMPUTING,2023,79(5):5403-5420.
APA	Bai, Qingchun,Xiao, Jun,&Zhou, Jie.(2023).A weakly supervised knowledge attentive network for aspect-level sentiment classification.JOURNAL OF SUPERCOMPUTING,79(5),5403-5420.
MLA	Bai, Qingchun,et al."A weakly supervised knowledge attentive network for aspect-level sentiment classification".JOURNAL OF SUPERCOMPUTING 79.5(2023):5403-5420.