Predicate-attention neural model for Chinese semantic role labeling

doi:10.1016/j.compeleceng.2022.107741

	Predicate-attention neural model for Chinese semantic role labeling
	Song, Heng 1,2; Wang, Shi 1; Liu, Yu 1,2; Wang, Ya 1,2
	2022-04-01
发表期刊	COMPUTERS & ELECTRICAL ENGINEERING
ISSN	0045-7906
卷号	99 页码:12
摘要	Semantic role labeling functions to convey the meaning of a sentence through forming a predicate-argument structure directed at the specific predicate. In recent years, end-toend semantic role labeling methods associated with the deep neural network have received significant attention in the field of computational linguistics. Moreover, end-to-end semantic role labeling methods have demonstrated a beneficial capacity to reduce the incompleteness caused by handcrafted features, which is an observed short-coming of traditional Chinese role labeling methods. However, the critical focus of sentences are frequently lost as a result of existing semantic role labeling structures attributing equal importance to every single word, instead of the overall concept denoted by particular terms. Hence, the performance and function ability of deep neural network models is reduced. In this paper, we introduce a specific attention mechanism based on the established predicate. This mechanism would automatically calculate the weighted contributions of each word, and the corresponding Part-of-Speech, in order to accurately represent the general fundamental ideas of the sentence. In addition, we extended the Bidirectional LSTM using two different semantic role constraint methods, to effectively utilize the dependency and constraint relationships among different semantic role tags, hereby further improving the performance of the whole neural Chinese semantic role labeling model. Experimental results demonstrate the efficacy of our proposed model through providing a baseline that allows for meaningful comparisons, inferring that both weighted contributions of the predicate, and semantic role constraints can help significantly refine the overall model function.
关键词	Chinese semantic role labeling Attention mechanism Argument identification Argument classification Semantic parsing
DOI	10.1016/j.compeleceng.2022.107741
收录类别	SCI
语种	英语
资助项目	Interdisciplinary Cooperation Project of Beijing Science and Technology New Star Program, China[Z191100001119014]
WOS研究方向	Computer Science ; Engineering
WOS类目	Computer Science, Hardware & Architecture ; Computer Science, Interdisciplinary Applications ; Engineering, Electrical & Electronic
WOS记录号	WOS:000754537600007
出版者	PERGAMON-ELSEVIER SCIENCE LTD
引用统计
文献类型	期刊论文
条目标识符	http://119.78.100.204/handle/2XEOYT63/18973
专题	中国科学院计算技术研究所期刊论文_英文
通讯作者	Wang, Shi
作者单位	1.Chinese Acad Sci, Inst Comp Technol, Key Lab Intelligent Informat Proc, Beijing, Peoples R China 2.Univ Chinese Acad Sci, Beijing, Peoples R China
推荐引用方式 GB/T 7714	Song, Heng,Wang, Shi,Liu, Yu,et al. Predicate-attention neural model for Chinese semantic role labeling[J]. COMPUTERS & ELECTRICAL ENGINEERING,2022,99:12.
APA	Song, Heng,Wang, Shi,Liu, Yu,&Wang, Ya.(2022).Predicate-attention neural model for Chinese semantic role labeling.COMPUTERS & ELECTRICAL ENGINEERING,99,12.
MLA	Song, Heng,et al."Predicate-attention neural model for Chinese semantic role labeling".COMPUTERS & ELECTRICAL ENGINEERING 99(2022):12.