Named Entity Recognition of Enterprise Annual Report Integrated with BERT

Automatically extracting key data from annual reports is an important means of business assessments. Aimed at the characteristics of complex entities, strong contextual semantics, and small scale of key entities in the field of corporate annual reports, a BERT-BiGRU-Attention-CRF model was proposed...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	ZHANG Jingyi, HE Guanghui, DAI Zhou, LIU Yadong
Formato:	article
Lenguaje:	ZH
Publicado:	Editorial Office of Journal of Shanghai Jiao Tong University 2021
Materias:	named entity recognition enterprise annual report bert attention mechanism bigru Engineering (General). Civil engineering (General) TA1-2040 Chemical engineering TP155-156 Naval architecture. Shipbuilding. Marine engineering VM1-989
Acceso en línea:	https://doaj.org/article/c4565136a5154fab92cc274152f36533
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:c4565136a5154fab92cc274152f36533
record_format	dspace
spelling	oai:doaj.org-article:c4565136a5154fab92cc274152f365332021-11-04T09:34:25ZNamed Entity Recognition of Enterprise Annual Report Integrated with BERT1006-246710.16183/j.cnki.jsjtu.2020.009https://doaj.org/article/c4565136a5154fab92cc274152f365332021-02-01T00:00:00Zhttp://xuebao.sjtu.edu.cn/CN/10.16183/j.cnki.jsjtu.2020.009https://doaj.org/toc/1006-2467Automatically extracting key data from annual reports is an important means of business assessments. Aimed at the characteristics of complex entities, strong contextual semantics, and small scale of key entities in the field of corporate annual reports, a BERT-BiGRU-Attention-CRF model was proposed to automatically identify and extract entities in the annual reports of enterprises. Based on the BiGRU-CRF model, the BERT pre-trained language model was used to enhance the generalization ability of the word vector model to capture long-range contextual information. Furthermore, the attention mechanism was used to fully mine the global and local features of the text. The experiment was performed on a self-constructed corporate annual report corpus, and the model was compared with multiple sets of models. The results show that the value of F1 (harmonic mean of precision and recall) of the BERT-BiGRU-Attention-CRF model is 93.69%. The model has a better performance than other traditional models in annual reports, and is expected to provide an automatic means for enterprise assessments.ZHANG JingyiHE GuanghuiDAI ZhouLIU YadongEditorial Office of Journal of Shanghai Jiao Tong Universityarticlenamed entity recognitionenterprise annual reportbertattention mechanismbigruEngineering (General). Civil engineering (General)TA1-2040Chemical engineeringTP155-156Naval architecture. Shipbuilding. Marine engineeringVM1-989ZHShanghai Jiaotong Daxue xuebao, Vol 55, Iss 02, Pp 117-123 (2021)
institution	DOAJ
collection	DOAJ
language	ZH
topic	named entity recognition enterprise annual report bert attention mechanism bigru Engineering (General). Civil engineering (General) TA1-2040 Chemical engineering TP155-156 Naval architecture. Shipbuilding. Marine engineering VM1-989
spellingShingle	named entity recognition enterprise annual report bert attention mechanism bigru Engineering (General). Civil engineering (General) TA1-2040 Chemical engineering TP155-156 Naval architecture. Shipbuilding. Marine engineering VM1-989 ZHANG Jingyi HE Guanghui DAI Zhou LIU Yadong Named Entity Recognition of Enterprise Annual Report Integrated with BERT
description	Automatically extracting key data from annual reports is an important means of business assessments. Aimed at the characteristics of complex entities, strong contextual semantics, and small scale of key entities in the field of corporate annual reports, a BERT-BiGRU-Attention-CRF model was proposed to automatically identify and extract entities in the annual reports of enterprises. Based on the BiGRU-CRF model, the BERT pre-trained language model was used to enhance the generalization ability of the word vector model to capture long-range contextual information. Furthermore, the attention mechanism was used to fully mine the global and local features of the text. The experiment was performed on a self-constructed corporate annual report corpus, and the model was compared with multiple sets of models. The results show that the value of F1 (harmonic mean of precision and recall) of the BERT-BiGRU-Attention-CRF model is 93.69%. The model has a better performance than other traditional models in annual reports, and is expected to provide an automatic means for enterprise assessments.
format	article
author	ZHANG Jingyi HE Guanghui DAI Zhou LIU Yadong
author_facet	ZHANG Jingyi HE Guanghui DAI Zhou LIU Yadong
author_sort	ZHANG Jingyi
title	Named Entity Recognition of Enterprise Annual Report Integrated with BERT
title_short	Named Entity Recognition of Enterprise Annual Report Integrated with BERT
title_full	Named Entity Recognition of Enterprise Annual Report Integrated with BERT
title_fullStr	Named Entity Recognition of Enterprise Annual Report Integrated with BERT
title_full_unstemmed	Named Entity Recognition of Enterprise Annual Report Integrated with BERT
title_sort	named entity recognition of enterprise annual report integrated with bert
publisher	Editorial Office of Journal of Shanghai Jiao Tong University
publishDate	2021
url	https://doaj.org/article/c4565136a5154fab92cc274152f36533
work_keys_str_mv	AT zhangjingyi namedentityrecognitionofenterpriseannualreportintegratedwithbert AT heguanghui namedentityrecognitionofenterpriseannualreportintegratedwithbert AT daizhou namedentityrecognitionofenterpriseannualreportintegratedwithbert AT liuyadong namedentityrecognitionofenterpriseannualreportintegratedwithbert
_version_	1718444990972035072

Named Entity Recognition of Enterprise Annual Report Integrated with BERT

Ejemplares similares