Joint entity and relation extraction based on a hybrid neural network

doi:10.1016/j.neucom.2016.12.075

	Joint entity and relation extraction based on a hybrid neural network
	Zheng, Suncong; Hao, Yuexing; Lu, Dongyuan; Bao, Hongyun; Xu, Jiaming; Hao, Hongwei; Xu, Bo
发表期刊	NEUROCOMPUTING
	2017-09-27
卷号	257 期号:000 页码:59-66
文章类型	Article
摘要	Entity and relation extraction is a task that combines detecting entity mentions and recognizing entities' semantic relationships from unstructured text. We propose a hybrid neural network model to extract entities and their relationships without any handcrafted features. The hybrid neural network contains a novel bidirectional encoder-decoder LSTM module (BiLSTM-ED) for entity extraction and a CNN module for relation classification. The contextual information of entities obtained in BiLSTM-ED further pass though to CNN module to improve the relation classification. We conduct experiments on the public dataset ACE05 (Automatic Content Extraction program) to verify the effectiveness of our method. The method we proposed achieves the state-of-the-art results on entity and relation extraction task. (C) 2017 Elsevier B.V. All rights reserved.
关键词	Neural Network Information Extraction Tagging Classification
WOS标题词	Science & Technology ; Technology
DOI	10.1016/j.neucom.2016.12.075
收录类别	SCI
语种	英语
WOS研究方向	Computer Science
WOS类目	Computer Science, Artificial Intelligence
WOS记录号	WOS:000404319800007
引用统计	被引频次：148[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://ir.ia.ac.cn/handle/173211/40796
专题	复杂系统认知与决策实验室_听觉模型与认知计算
推荐引用方式 GB/T 7714	Zheng, Suncong,Hao, Yuexing,Lu, Dongyuan,et al. Joint entity and relation extraction based on a hybrid neural network[J]. NEUROCOMPUTING,2017,257(000):59-66.
APA	Zheng, Suncong.,Hao, Yuexing.,Lu, Dongyuan.,Bao, Hongyun.,Xu, Jiaming.,...&Xu, Bo.(2017).Joint entity and relation extraction based on a hybrid neural network.NEUROCOMPUTING,257(000),59-66.
MLA	Zheng, Suncong,et al."Joint entity and relation extraction based on a hybrid neural network".NEUROCOMPUTING 257.000(2017):59-66.