An ERNIE-Based Joint Model for Chinese Named Entity Recognition

doi:10.3390/app10165711

	An ERNIE-Based Joint Model for Chinese Named Entity Recognition
	Wang, Yu 1,2; Sun, Yining 1,2; Ma, Zuchang 2; Gao, Lisheng 2; Xu, Yang 2
刊名	APPLIED SCIENCES-BASEL
	2020-08-01
卷号	10
关键词	joint training named entity recognition pre-training models ERNIE BERT
DOI	10.3390/app10165711
通讯作者	Sun, Yining(ynsun@iim.ac.cn)
英文摘要	Named Entity Recognition (NER) is the fundamental task for Natural Language Processing (NLP) and the initial step in building a Knowledge Graph (KG). Recently, BERT (Bidirectional Encoder Representations from Transformers), which is a pre-training model, has achieved state-of-the-art (SOTA) results in various NLP tasks, including the NER. However, Chinese NER is still a more challenging task for BERT because there are no physical separations between Chinese words, and BERT can only obtain the representations of Chinese characters. Nevertheless, the Chinese NER cannot be well handled with character-level representations, because the meaning of a Chinese word is quite different from that of the characters, which make up the word. ERNIE (Enhanced Representation through kNowledge IntEgration), which is an improved pre-training model of BERT, is more suitable for Chinese NER because it is designed to learn language representations enhanced by the knowledge masking strategy. However, the potential of ERNIE has not been fully explored. ERNIE only utilizes the token-level features and ignores the sentence-level feature when performing the NER task. In this paper, we propose the ERNIE-Joint, which is a joint model based on ERNIE. The ERNIE-Joint can utilize both the sentence-level and token-level features by joint training the NER and text classification tasks. In order to use the raw NER datasets for joint training and avoid additional annotations, we perform the text classification task according to the number of entities in the sentences. The experiments are conducted on two datasets: MSRA-NER and Weibo. These datasets contain Chinese news data and Chinese social media data, respectively. The results demonstrate that the ERNIE-Joint not only outperforms BERT and ERNIE but also achieves the SOTA results on both datasets.
资助项目	major special project of Anhui Science and Technology Department[18030801133] ; Science and Technology Service Network Initiative[KFJ-STS-ZDTP-079]
WOS研究方向	Chemistry ; Engineering ; Materials Science ; Physics
语种	英语
出版者	MDPI
WOS记录号	WOS:000567143300001
资助机构	major special project of Anhui Science and Technology Department ; Science and Technology Service Network Initiative
内容类型	期刊论文
源URL	[http://ir.hfcas.ac.cn:8080/handle/334002/104066]
专题	中国科学院合肥物质科学研究院
通讯作者	Sun, Yining
作者单位	1.Univ Sci & Technol China, Grad Sch, Sci Isl Branch, Hefei 230026, Peoples R China 2.Chinese Acad Sci, Inst Intelligent Machines, Hefei Inst Phys Sci, AnHui Prov Key Lab Med Phys & Technol, Hefei 230031, Peoples R China
推荐引用方式 GB/T 7714	Wang, Yu,Sun, Yining,Ma, Zuchang,et al. An ERNIE-Based Joint Model for Chinese Named Entity Recognition[J]. APPLIED SCIENCES-BASEL,2020,10.
APA	Wang, Yu,Sun, Yining,Ma, Zuchang,Gao, Lisheng,&Xu, Yang.(2020).An ERNIE-Based Joint Model for Chinese Named Entity Recognition.APPLIED SCIENCES-BASEL,10.
MLA	Wang, Yu,et al."An ERNIE-Based Joint Model for Chinese Named Entity Recognition".APPLIED SCIENCES-BASEL 10(2020).