A joint model for medical named entity recognition and normalization

Ying Xiong; Yuanhang Huang; Qingcai Chen; Xiaolong Wang; Yuan Ni; Buzhou Tang

A joint model for medical named entity recognition and normalization

Ying Xiong
, Yuanhang Huang
, Qingcai Chen
, Xiaolong Wang
, Yuan Ni
, Buzhou Tang^*

^*Corresponding author for this work

Harbin Institute of Technology Shenzhen
PingAn Health Technology Ltd

Research output: Contribution to journal › Conference article › peer-review

8 Scopus citations

Abstract

Traditional pipeline models for medical named entity recognition and normalization (MER and MEN) suffer from error propagation. To tackle the error propagation problem, we propose a novel joint deep learning method for the 2020 IberLEF shared task on MER and MEN, where MER is regarded as a machine reading comprehension (MRC) problem and MEN as multiple sequence labeling problems corresponding to normalized hierarchical tumor codes. In the 2020 IberLEF shared task, our proposed joint model achieves an F1 score of 0.87 on MER and an F1 score of 0.825 on MEN, and significantly outperforms pipeline models for comparison.

Original language	English
Pages (from-to)	499-504
Number of pages	6
Journal	CEUR Workshop Proceedings
Volume	2664
State	Published - 2020
Externally published	Yes
Event	2020 Iberian Languages Evaluation Forum, IberLEF 2020 - Malaga, Spain Duration: 23 Sep 2020 → …

Keywords

Joint deep learning
Medica named entity recognition
Medical entity normalization
Multiple sequence labeling

Cite this

@article{0532bd495dd34f5486937d39748b42c8,

title = "A joint model for medical named entity recognition and normalization",

abstract = "Traditional pipeline models for medical named entity recognition and normalization (MER and MEN) suffer from error propagation. To tackle the error propagation problem, we propose a novel joint deep learning method for the 2020 IberLEF shared task on MER and MEN, where MER is regarded as a machine reading comprehension (MRC) problem and MEN as multiple sequence labeling problems corresponding to normalized hierarchical tumor codes. In the 2020 IberLEF shared task, our proposed joint model achieves an F1 score of 0.87 on MER and an F1 score of 0.825 on MEN, and significantly outperforms pipeline models for comparison.",

keywords = "Joint deep learning, Medica named entity recognition, Medical entity normalization, Multiple sequence labeling",

author = "Ying Xiong and Yuanhang Huang and Qingcai Chen and Xiaolong Wang and Yuan Ni and Buzhou Tang",

note = "Publisher Copyright: {\textcopyright} 2020 Copyright for this paper by its authors. Use permitted under.; 2020 Iberian Languages Evaluation Forum, IberLEF 2020 ; Conference date: 23-09-2020",

year = "2020",

language = "英语",

volume = "2664",

pages = "499--504",

journal = "CEUR Workshop Proceedings",

issn = "1613-0073",

publisher = "CEUR-WS",

}

TY - JOUR

T1 - A joint model for medical named entity recognition and normalization

AU - Xiong, Ying

AU - Huang, Yuanhang

AU - Chen, Qingcai

AU - Wang, Xiaolong

AU - Ni, Yuan

AU - Tang, Buzhou

PY - 2020

Y1 - 2020

N2 - Traditional pipeline models for medical named entity recognition and normalization (MER and MEN) suffer from error propagation. To tackle the error propagation problem, we propose a novel joint deep learning method for the 2020 IberLEF shared task on MER and MEN, where MER is regarded as a machine reading comprehension (MRC) problem and MEN as multiple sequence labeling problems corresponding to normalized hierarchical tumor codes. In the 2020 IberLEF shared task, our proposed joint model achieves an F1 score of 0.87 on MER and an F1 score of 0.825 on MEN, and significantly outperforms pipeline models for comparison.

AB - Traditional pipeline models for medical named entity recognition and normalization (MER and MEN) suffer from error propagation. To tackle the error propagation problem, we propose a novel joint deep learning method for the 2020 IberLEF shared task on MER and MEN, where MER is regarded as a machine reading comprehension (MRC) problem and MEN as multiple sequence labeling problems corresponding to normalized hierarchical tumor codes. In the 2020 IberLEF shared task, our proposed joint model achieves an F1 score of 0.87 on MER and an F1 score of 0.825 on MEN, and significantly outperforms pipeline models for comparison.

KW - Joint deep learning

KW - Medica named entity recognition

KW - Medical entity normalization

KW - Multiple sequence labeling

UR - https://www.scopus.com/pages/publications/85092240098

M3 - 会议文章

AN - SCOPUS:85092240098

SN - 1613-0073

VL - 2664

SP - 499

EP - 504

JO - CEUR Workshop Proceedings

JF - CEUR Workshop Proceedings

T2 - 2020 Iberian Languages Evaluation Forum, IberLEF 2020

Y2 - 23 September 2020

ER -

A joint model for medical named entity recognition and normalization

Abstract

Keywords

Other files and links

Fingerprint

Cite this