A Gated Dilated Convolution with Attention Model for Clinical Cloze-Style Reading Comprehension

The machine comprehension research of clinical medicine has great potential value in practical application, but it has not received sufficient attention and many existing models are very time consuming for the cloze-style machine reading comprehension. In this paper, we study the cloze-style machine...

Full description

Bibliographic Details
Main Authors:	Bin Wang, Xuejie Zhang, Xiaobing Zhou, Junyi Li
Format:	Article
Language:	English
Published:	MDPI AG 2020-02-01
Series:	International Journal of Environmental Research and Public Health
Subjects:	clinical medicine machine reading comprehension cloze-style gated dilated convolution attention mechanism
Online Access:	https://www.mdpi.com/1660-4601/17/4/1323

id	doaj-73d3771712ba49808c76447007e893d4
record_format	Article
spelling	doaj-73d3771712ba49808c76447007e893d42020-11-25T02:36:04ZengMDPI AGInternational Journal of Environmental Research and Public Health1660-46012020-02-01174132310.3390/ijerph17041323ijerph17041323A Gated Dilated Convolution with Attention Model for Clinical Cloze-Style Reading ComprehensionBin Wang0Xuejie Zhang1Xiaobing Zhou2Junyi Li3School of Information Science and Engineering, Yunnan University, Kunming 650091, ChinaSchool of Information Science and Engineering, Yunnan University, Kunming 650091, ChinaSchool of Information Science and Engineering, Yunnan University, Kunming 650091, ChinaSchool of Information Science and Engineering, Yunnan University, Kunming 650091, ChinaThe machine comprehension research of clinical medicine has great potential value in practical application, but it has not received sufficient attention and many existing models are very time consuming for the cloze-style machine reading comprehension. In this paper, we study the cloze-style machine reading comprehension in the clinical medical field and propose a Gated Dilated Convolution with Attention (GDCA) model, which consists of a gated dilated convolution module and an attention mechanism. Our model has high parallelism and is capable of capturing long-distance dependencies. On the CliCR data set, our model surpasses the present best model on several metrics and obtains state-of-the-art result, and the training speed is 8 times faster than that of the best model.https://www.mdpi.com/1660-4601/17/4/1323clinical medicinemachine reading comprehensioncloze-stylegated dilated convolutionattention mechanism
collection	DOAJ
language	English
format	Article
sources	DOAJ
author	Bin Wang Xuejie Zhang Xiaobing Zhou Junyi Li
spellingShingle	Bin Wang Xuejie Zhang Xiaobing Zhou Junyi Li A Gated Dilated Convolution with Attention Model for Clinical Cloze-Style Reading Comprehension International Journal of Environmental Research and Public Health clinical medicine machine reading comprehension cloze-style gated dilated convolution attention mechanism
author_facet	Bin Wang Xuejie Zhang Xiaobing Zhou Junyi Li
author_sort	Bin Wang
title	A Gated Dilated Convolution with Attention Model for Clinical Cloze-Style Reading Comprehension
title_short	A Gated Dilated Convolution with Attention Model for Clinical Cloze-Style Reading Comprehension
title_full	A Gated Dilated Convolution with Attention Model for Clinical Cloze-Style Reading Comprehension
title_fullStr	A Gated Dilated Convolution with Attention Model for Clinical Cloze-Style Reading Comprehension
title_full_unstemmed	A Gated Dilated Convolution with Attention Model for Clinical Cloze-Style Reading Comprehension
title_sort	gated dilated convolution with attention model for clinical cloze-style reading comprehension
publisher	MDPI AG
series	International Journal of Environmental Research and Public Health
issn	1660-4601
publishDate	2020-02-01
description	The machine comprehension research of clinical medicine has great potential value in practical application, but it has not received sufficient attention and many existing models are very time consuming for the cloze-style machine reading comprehension. In this paper, we study the cloze-style machine reading comprehension in the clinical medical field and propose a Gated Dilated Convolution with Attention (GDCA) model, which consists of a gated dilated convolution module and an attention mechanism. Our model has high parallelism and is capable of capturing long-distance dependencies. On the CliCR data set, our model surpasses the present best model on several metrics and obtains state-of-the-art result, and the training speed is 8 times faster than that of the best model.
topic	clinical medicine machine reading comprehension cloze-style gated dilated convolution attention mechanism
url	https://www.mdpi.com/1660-4601/17/4/1323
work_keys_str_mv	AT binwang agateddilatedconvolutionwithattentionmodelforclinicalclozestylereadingcomprehension AT xuejiezhang agateddilatedconvolutionwithattentionmodelforclinicalclozestylereadingcomprehension AT xiaobingzhou agateddilatedconvolutionwithattentionmodelforclinicalclozestylereadingcomprehension AT junyili agateddilatedconvolutionwithattentionmodelforclinicalclozestylereadingcomprehension AT binwang gateddilatedconvolutionwithattentionmodelforclinicalclozestylereadingcomprehension AT xuejiezhang gateddilatedconvolutionwithattentionmodelforclinicalclozestylereadingcomprehension AT xiaobingzhou gateddilatedconvolutionwithattentionmodelforclinicalclozestylereadingcomprehension AT junyili gateddilatedconvolutionwithattentionmodelforclinicalclozestylereadingcomprehension
_version_	1724801503051382784

A Gated Dilated Convolution with Attention Model for Clinical Cloze-Style Reading Comprehension

Similar Items