Multi-task Character-Level Attentional Networks for Medical Concept Normalization

doi:10.1007/s11063-018-9873-x

	Multi-task Character-Level Attentional Networks for Medical Concept Normalization
	Niu, Jinghao1,2 ; Yang, Yehui1,2 ; Zhang, Siheng1,2 ; Sun, Zhengya1,2 ; Zhang, Wensheng1,2
刊名	NEURAL PROCESSING LETTERS
	2019-06-01
卷号	49 期号:3 页码:1239-1256
关键词	Convolutional neural network Multi-task learning Medical concept normalization
ISSN号	1370-4621
DOI	10.1007/s11063-018-9873-x
通讯作者	Zhang, Wensheng(zhangwenshengia@hotmail.com)
英文摘要	Recognizing standard medical concepts in the colloquial text is significant for kinds of applications such as the medical question answering system. Recently, word-level neural network methods, which can learn complex informal expression features, achieved remarkable performance on this task. However, they have two main limitations: (1) Existing word-level methods cannot learn character structure features inside words and suffer from "Out-of-vocabulary" (OOV) words, which are common in noisy colloquial text. (2) Since these methods handle the normalization task as a classification issue, concept phrases are represented by category labels. Hence theword morphological information inside the concept is lost. In this work, we present a multi-task character-level attentional network model for medical concept normalization. Specifically, the character-level encoding scheme of our model can alleviate the OOV word problem. The attention mechanism can effectively exploit thewordmorphological information through multi-task training. It generates higher attention weights on domain-related positions in the text sequence, helping the downstream convolution focus on the characters that are related to medical concepts. To test our model, we first introduce a labeled Chinese dataset (overall 314,991 records) for this task. Other two realworld English datasets are also used. Our model outperforms state-of-the-art methods on all three datasets. Besides, by adding four types noises to the datasets, we validate the robustness of our model against common noises in the colloquial text.
资助项目	National Natural Science Foundation of China[61472423] ; National Natural Science Foundation of China[61432008] ; National Natural Science Foundation of China[U1636220] ; Beijing Municipal Natural Science Foundation[4172063]
WOS研究方向	Computer Science
语种	英语
出版者	SPRINGER
WOS记录号	WOS:000483206800024
资助机构	National Natural Science Foundation of China ; Beijing Municipal Natural Science Foundation
内容类型	期刊论文
源URL	[http://ir.ia.ac.cn/handle/173211/27202]
专题	中国科学院自动化研究所
通讯作者	Zhang, Wensheng
作者单位	1.Univ Chinese Acad Sci, Beijing, Peoples R China 2.Chinese Acad Sci, Inst Automat, 95 Zhongguancun East Rd, Beijing 100190, Peoples R China
推荐引用方式 GB/T 7714	Niu, Jinghao,Yang, Yehui,Zhang, Siheng,et al. Multi-task Character-Level Attentional Networks for Medical Concept Normalization[J]. NEURAL PROCESSING LETTERS,2019,49(3):1239-1256.
APA	Niu, Jinghao,Yang, Yehui,Zhang, Siheng,Sun, Zhengya,&Zhang, Wensheng.(2019).Multi-task Character-Level Attentional Networks for Medical Concept Normalization.NEURAL PROCESSING LETTERS,49(3),1239-1256.
MLA	Niu, Jinghao,et al."Multi-task Character-Level Attentional Networks for Medical Concept Normalization".NEURAL PROCESSING LETTERS 49.3(2019):1239-1256.