A MULTI-TASK LEARNING FRAMEWORK FOR CHINESE MEDICAL PROCEDURE ENTITY NORMALIZATION

被引：3

作者：

Sui, Xuhui ^{[1
]}

Song, Kehui ^{[1
]}

Zhou, Baohang ^{[1
]}

Zhang, Ying ^{[1
]}

Yuan, Xiaojie ^{[1
]}

机构：

[1] Nankai Univ, Coll Comp Sci, TKLNDST, Tianjin, Peoples R China

来源：

2022 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP) | 2022年

关键词：

Named entity normalization; Chinese medical data; Text mining; Joint modeling framework;

D O I：

10.1109/ICASSP43922.2022.9747858

中图分类号：

O42 [声学];

学科分类号：

070206 ; 082403 ;

摘要：

Medical entity normalization is a fundamental task in medical natural language processing and clinical applications. The task aims to map medical mentions to standard entities in a given knowledge base. In this paper, we focus on Chinese medical procedure entity normalization. This task brings an extra multi-implication challenge that a mention may link to multiple standard entities. To perform the task, we propose a novel deep neural multi-task learning framework to jointly model implication number prediction and entity normalization. Our model utilizes the multi-head attention mechanism to provide mutual benefits between the two tasks. Experimental results show that our method achieves comparable performance compared with the baseline methods.

引用

页码：8337 / 8341

页数：5