Exploiting global contextual information for document-level named entity recognition

doi:10.1016/j.knosys.2023.111266

	Exploiting global contextual information for document-level named entity recognition
	Yu, Yiting 1; Wang, Zanbo 1; Wei, Wei 1; Zhang, Ruihan 1; Mao, Xian-Ling 2; Feng, Shanshan 3; Wang, Fei 4; He, Zhiyong 5; Jiang, Sheng 1
	2024-01-25
发表期刊	KNOWLEDGE-BASED SYSTEMS
ISSN	0950-7051
卷号	284 页码:10
摘要	Named entity recognition (NER, also known as entity chunking/extraction) is a fundamental sub-task of information extraction, which aims at identifying named entities from an unstructured text into pre-defined classes. Most of the existing works mainly focus on modeling local-context dependencies in a single sentence for entity type prediction. However, they may neglect the clues derived from other sentences within a document, and thus suffer from the sentence-level inherent ambiguity issue, which may make their performance drop to some extent. To this end, we propose a Global Context enhanced Document-level NER (GCDoc) model for NER to fully exploit the global contextual information of a document in different levels, i.e., word-level and sentence-level. Specifically, GCDoc constructs a document graph to capture the global dependencies of words for enriching the representations of each word in word-level. Then, it encodes the adjacent sentences for exploring the contexts across sentences to enhance the representation of the current sentence via the specially devised attention mechanism. Extensive experiments on two benchmark NER datasets (i.e., CoNLL 2003 and Onenotes 5.0 English dataset) demonstrate the effectiveness of our proposed model, as compared to the competitive baselines.
关键词	Named entity recognition Global contextual information Graph neural network Epistemic uncertainty
DOI	10.1016/j.knosys.2023.111266
收录类别	SCI
语种	英语
资助项目	National Natural Science Foundation of China[62276110] ; National Natural Science Foundation of China[62172039] ; Joint Laboratory of HUST and Pingan Property & Casualty Research (HPL)
WOS研究方向	Computer Science
WOS类目	Computer Science, Artificial Intelligence
WOS记录号	WOS:001132970800001
出版者	ELSEVIER
引用统计	被引频次：2[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://119.78.100.204/handle/2XEOYT63/38434
专题	中国科学院计算技术研究所期刊论文_英文
通讯作者	Wei, Wei
作者单位	1.Huazhong Univ Sci & Technol, Sch Comp Sci & Technol, Cognit Comp & Intelligent Informat Proc CCIIP Lab, Wuhan, Peoples R China 2.Beijing Inst Technol, Dept Comp Sci & Technol, Beijing, Peoples R China 3.ASTAR, Ctr Frontier AI Res, IHPC, Singapore City, Singapore 4.Chinese Acad Sci, Inst Comp Technol, Beijing, Peoples R China 5.Naval Univ Engn, Sch Elect Engn, Wuhan, Peoples R China
推荐引用方式 GB/T 7714	Yu, Yiting,Wang, Zanbo,Wei, Wei,et al. Exploiting global contextual information for document-level named entity recognition[J]. KNOWLEDGE-BASED SYSTEMS,2024,284:10.
APA	Yu, Yiting.,Wang, Zanbo.,Wei, Wei.,Zhang, Ruihan.,Mao, Xian-Ling.,...&Jiang, Sheng.(2024).Exploiting global contextual information for document-level named entity recognition.KNOWLEDGE-BASED SYSTEMS,284,10.
MLA	Yu, Yiting,et al."Exploiting global contextual information for document-level named entity recognition".KNOWLEDGE-BASED SYSTEMS 284(2024):10.