Utilizing Entity-Based Gated Convolution and Multilevel Sentence Attention to Improve Distantly Supervised Relation Extraction

Distant supervision is an effective method to automatically collect large-scale datasets for relation extraction (RE). Automatically constructed datasets usually comprise two types of noise: the intrasentence noise and the wrongly labeled noisy sentence. To address issues caused by the above two typ...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Qian Yi, Guixuan Zhang, Shuwu Zhang
Formato:	article
Lenguaje:	EN
Publicado:	Hindawi Limited 2021
Materias:	Computer applications to medicine. Medical informatics R858-859.7 Neurosciences. Biological psychiatry. Neuropsychiatry RC321-571
Acceso en línea:	https://doaj.org/article/b204ab2d882d4948853196e216dba7bd
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:b204ab2d882d4948853196e216dba7bd
record_format	dspace
spelling	oai:doaj.org-article:b204ab2d882d4948853196e216dba7bd2021-11-15T01:19:44ZUtilizing Entity-Based Gated Convolution and Multilevel Sentence Attention to Improve Distantly Supervised Relation Extraction1687-527310.1155/2021/6110885https://doaj.org/article/b204ab2d882d4948853196e216dba7bd2021-01-01T00:00:00Zhttp://dx.doi.org/10.1155/2021/6110885https://doaj.org/toc/1687-5273Distant supervision is an effective method to automatically collect large-scale datasets for relation extraction (RE). Automatically constructed datasets usually comprise two types of noise: the intrasentence noise and the wrongly labeled noisy sentence. To address issues caused by the above two types of noise and improve distantly supervised relation extraction, this paper proposes a novel distantly supervised relation extraction model, which consists of an entity-based gated convolution sentence encoder and a multilevel sentence selective attention (Matt) module. Specifically, we first apply an entity-based gated convolution operation to force the sentence encoder to extract entity-pair-related features and filter out useless intrasentence noise information. Furthermore, the multilevel attention schema fuses the bag information to obtain a fine-grained bag-specific query vector, which can better identify valid sentences and reduce the influence of wrongly labeled sentences. Experimental results on a large-scale benchmark dataset show that our model can effectively reduce the influence of the above two types of noise and achieves state-of-the-art performance in relation extraction.Qian YiGuixuan ZhangShuwu ZhangHindawi LimitedarticleComputer applications to medicine. Medical informaticsR858-859.7Neurosciences. Biological psychiatry. NeuropsychiatryRC321-571ENComputational Intelligence and Neuroscience, Vol 2021 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Computer applications to medicine. Medical informatics R858-859.7 Neurosciences. Biological psychiatry. Neuropsychiatry RC321-571
spellingShingle	Computer applications to medicine. Medical informatics R858-859.7 Neurosciences. Biological psychiatry. Neuropsychiatry RC321-571 Qian Yi Guixuan Zhang Shuwu Zhang Utilizing Entity-Based Gated Convolution and Multilevel Sentence Attention to Improve Distantly Supervised Relation Extraction
description	Distant supervision is an effective method to automatically collect large-scale datasets for relation extraction (RE). Automatically constructed datasets usually comprise two types of noise: the intrasentence noise and the wrongly labeled noisy sentence. To address issues caused by the above two types of noise and improve distantly supervised relation extraction, this paper proposes a novel distantly supervised relation extraction model, which consists of an entity-based gated convolution sentence encoder and a multilevel sentence selective attention (Matt) module. Specifically, we first apply an entity-based gated convolution operation to force the sentence encoder to extract entity-pair-related features and filter out useless intrasentence noise information. Furthermore, the multilevel attention schema fuses the bag information to obtain a fine-grained bag-specific query vector, which can better identify valid sentences and reduce the influence of wrongly labeled sentences. Experimental results on a large-scale benchmark dataset show that our model can effectively reduce the influence of the above two types of noise and achieves state-of-the-art performance in relation extraction.
format	article
author	Qian Yi Guixuan Zhang Shuwu Zhang
author_facet	Qian Yi Guixuan Zhang Shuwu Zhang
author_sort	Qian Yi
title	Utilizing Entity-Based Gated Convolution and Multilevel Sentence Attention to Improve Distantly Supervised Relation Extraction
title_short	Utilizing Entity-Based Gated Convolution and Multilevel Sentence Attention to Improve Distantly Supervised Relation Extraction
title_full	Utilizing Entity-Based Gated Convolution and Multilevel Sentence Attention to Improve Distantly Supervised Relation Extraction
title_fullStr	Utilizing Entity-Based Gated Convolution and Multilevel Sentence Attention to Improve Distantly Supervised Relation Extraction
title_full_unstemmed	Utilizing Entity-Based Gated Convolution and Multilevel Sentence Attention to Improve Distantly Supervised Relation Extraction
title_sort	utilizing entity-based gated convolution and multilevel sentence attention to improve distantly supervised relation extraction
publisher	Hindawi Limited
publishDate	2021
url	https://doaj.org/article/b204ab2d882d4948853196e216dba7bd
work_keys_str_mv	AT qianyi utilizingentitybasedgatedconvolutionandmultilevelsentenceattentiontoimprovedistantlysupervisedrelationextraction AT guixuanzhang utilizingentitybasedgatedconvolutionandmultilevelsentenceattentiontoimprovedistantlysupervisedrelationextraction AT shuwuzhang utilizingentitybasedgatedconvolutionandmultilevelsentenceattentiontoimprovedistantlysupervisedrelationextraction
_version_	1718428943527182336

Utilizing Entity-Based Gated Convolution and Multilevel Sentence Attention to Improve Distantly Supervised Relation Extraction

Ejemplares similares