Fine-Grained Named Entity Recognition Using a Multi-Stacked Feature Fusion and Dual-Stacked Output in Korean

Named entity recognition (NER) is a natural language processing task to identify spans that mention named entities and to annotate them with predefined named entity classes. Although many NER models based on machine learning have been proposed, their performance in terms of processing fine-grained N...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Hongjin Kim, Harksoo Kim
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	fine-grained named entity recognition k-stacked feature fusion dual-stacked output unbalanced data problem Technology T Engineering (General). Civil engineering (General) TA1-2040 Biology (General) QH301-705.5 Physics QC1-999 Chemistry QD1-999
Acceso en línea:	https://doaj.org/article/d5945ab22afa400fa1c085485e8264e0
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:d5945ab22afa400fa1c085485e8264e0
record_format	dspace
spelling	oai:doaj.org-article:d5945ab22afa400fa1c085485e8264e02021-11-25T16:38:17ZFine-Grained Named Entity Recognition Using a Multi-Stacked Feature Fusion and Dual-Stacked Output in Korean10.3390/app1122107952076-3417https://doaj.org/article/d5945ab22afa400fa1c085485e8264e02021-11-01T00:00:00Zhttps://www.mdpi.com/2076-3417/11/22/10795https://doaj.org/toc/2076-3417Named entity recognition (NER) is a natural language processing task to identify spans that mention named entities and to annotate them with predefined named entity classes. Although many NER models based on machine learning have been proposed, their performance in terms of processing fine-grained NER tasks was less than acceptable. This is because the training data of a fine-grained NER task is much more unbalanced than those of a coarse-grained NER task. To overcome the problem presented by unbalanced data, we propose a fine-grained NER model that compensates for the sparseness of fine-grained NEs by using the contextual information of coarse-grained NEs. From another viewpoint, many NER models have used different levels of features, such as part-of-speech tags and gazetteer look-up results, in a nonhierarchical manner. Unfortunately, these models experience the feature interference problem. Our solution to this problem is to adopt a multi-stacked feature fusion scheme, which accepts different levels of features as its input. The proposed model is based on multi-stacked long short-term memories (LSTMs) with a multi-stacked feature fusion layer for acquiring multilevel embeddings and a dual-stacked output layer for predicting fine-grained NEs based on the categorical information of coarse-grained NEs. Our experiments indicate that the proposed model is capable of state-of-the-art performance. The results show that the proposed model can effectively alleviate the unbalanced data problem that frequently occurs in a fine-grained NER task. In addition, the multi-stacked feature fusion layer contributes to the improvement of NER performance, confirming that the proposed model can alleviate the feature interference problem. Based on this experimental result, we conclude that the proposed model is well-designed to effectively perform NER tasks.Hongjin KimHarksoo KimMDPI AGarticlefine-grained named entity recognitionk-stacked feature fusiondual-stacked outputunbalanced data problemTechnologyTEngineering (General). Civil engineering (General)TA1-2040Biology (General)QH301-705.5PhysicsQC1-999ChemistryQD1-999ENApplied Sciences, Vol 11, Iss 10795, p 10795 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	fine-grained named entity recognition k-stacked feature fusion dual-stacked output unbalanced data problem Technology T Engineering (General). Civil engineering (General) TA1-2040 Biology (General) QH301-705.5 Physics QC1-999 Chemistry QD1-999
spellingShingle	fine-grained named entity recognition k-stacked feature fusion dual-stacked output unbalanced data problem Technology T Engineering (General). Civil engineering (General) TA1-2040 Biology (General) QH301-705.5 Physics QC1-999 Chemistry QD1-999 Hongjin Kim Harksoo Kim Fine-Grained Named Entity Recognition Using a Multi-Stacked Feature Fusion and Dual-Stacked Output in Korean
description	Named entity recognition (NER) is a natural language processing task to identify spans that mention named entities and to annotate them with predefined named entity classes. Although many NER models based on machine learning have been proposed, their performance in terms of processing fine-grained NER tasks was less than acceptable. This is because the training data of a fine-grained NER task is much more unbalanced than those of a coarse-grained NER task. To overcome the problem presented by unbalanced data, we propose a fine-grained NER model that compensates for the sparseness of fine-grained NEs by using the contextual information of coarse-grained NEs. From another viewpoint, many NER models have used different levels of features, such as part-of-speech tags and gazetteer look-up results, in a nonhierarchical manner. Unfortunately, these models experience the feature interference problem. Our solution to this problem is to adopt a multi-stacked feature fusion scheme, which accepts different levels of features as its input. The proposed model is based on multi-stacked long short-term memories (LSTMs) with a multi-stacked feature fusion layer for acquiring multilevel embeddings and a dual-stacked output layer for predicting fine-grained NEs based on the categorical information of coarse-grained NEs. Our experiments indicate that the proposed model is capable of state-of-the-art performance. The results show that the proposed model can effectively alleviate the unbalanced data problem that frequently occurs in a fine-grained NER task. In addition, the multi-stacked feature fusion layer contributes to the improvement of NER performance, confirming that the proposed model can alleviate the feature interference problem. Based on this experimental result, we conclude that the proposed model is well-designed to effectively perform NER tasks.
format	article
author	Hongjin Kim Harksoo Kim
author_facet	Hongjin Kim Harksoo Kim
author_sort	Hongjin Kim
title	Fine-Grained Named Entity Recognition Using a Multi-Stacked Feature Fusion and Dual-Stacked Output in Korean
title_short	Fine-Grained Named Entity Recognition Using a Multi-Stacked Feature Fusion and Dual-Stacked Output in Korean
title_full	Fine-Grained Named Entity Recognition Using a Multi-Stacked Feature Fusion and Dual-Stacked Output in Korean
title_fullStr	Fine-Grained Named Entity Recognition Using a Multi-Stacked Feature Fusion and Dual-Stacked Output in Korean
title_full_unstemmed	Fine-Grained Named Entity Recognition Using a Multi-Stacked Feature Fusion and Dual-Stacked Output in Korean
title_sort	fine-grained named entity recognition using a multi-stacked feature fusion and dual-stacked output in korean
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/d5945ab22afa400fa1c085485e8264e0
work_keys_str_mv	AT hongjinkim finegrainednamedentityrecognitionusingamultistackedfeaturefusionanddualstackedoutputinkorean AT harksookim finegrainednamedentityrecognitionusingamultistackedfeaturefusionanddualstackedoutputinkorean
_version_	1718413106384732160

Fine-Grained Named Entity Recognition Using a Multi-Stacked Feature Fusion and Dual-Stacked Output in Korean

Ejemplares similares