Evaluating Medical Lexical Simplification: Rule-Based vs. BERT

Linh Tran; Erick Velazquez; Robert Jan Sips; Victor de Boer

doi:10.3233/SHTI210337

Evaluating Medical Lexical Simplification: Rule-Based vs. BERT

Linh Tran, Erick Velazquez, Robert Jan Sips, Victor de Boer

Research output: Chapter in Book / Report / Conference proceeding › Chapter › Academic › peer-review

Abstract

Lexical simplification (LS) can decrease the communication gap between medical experts and laypeople by replacing medical terms with layperson counterparts. In this paper, we present: 1) a rule-based approach to LS using a consumer health vocabulary, and 2) an unsupervised approach using BERT to generate word candidates. Human evaluation shows that the unsupervised model performed better for simplicity and grammaticality, while the rule-based method was better at meaning preservation.

Original language	English
Title of host publication	Public Health and Informatics
Editors	Jan Mantas
Publisher	IOS Press
Pages	1023-1024
Number of pages	2
ISBN (Electronic)	9781643681856
ISBN (Print)	9781643681849
DOIs	https://doi.org/10.3233/SHTI210337
Publication status	Published - 2021

Publication series

Name	Studies in health technology and informatics
Publisher	IOS Press
Volume	281

Bibliographical note

Copyright:
This record is sourced from MEDLINE/PubMed, a database of the U.S. National Library of Medicine

Keywords

Health Vocabulary
Lexical Simplification
Machine Learning

Access to Document

10.3233/SHTI210337

Persistent URL (handle)

Persistent link

Cite this

@inbook{2b25e8ea996344f29803f511007a0001,

title = "Evaluating Medical Lexical Simplification: Rule-Based vs. BERT",

abstract = "Lexical simplification (LS) can decrease the communication gap between medical experts and laypeople by replacing medical terms with layperson counterparts. In this paper, we present: 1) a rule-based approach to LS using a consumer health vocabulary, and 2) an unsupervised approach using BERT to generate word candidates. Human evaluation shows that the unsupervised model performed better for simplicity and grammaticality, while the rule-based method was better at meaning preservation.",

keywords = "Health Vocabulary, Lexical Simplification, Machine Learning",

author = "Linh Tran and Erick Velazquez and Sips, {Robert Jan} and {de Boer}, Victor",

note = "Copyright: This record is sourced from MEDLINE/PubMed, a database of the U.S. National Library of Medicine",

year = "2021",

doi = "10.3233/SHTI210337",

language = "English",

isbn = "9781643681849",

series = "Studies in health technology and informatics",

publisher = "IOS Press",

pages = "1023--1024",

editor = "Jan Mantas",

booktitle = "Public Health and Informatics",

}

TY - CHAP

T1 - Evaluating Medical Lexical Simplification: Rule-Based vs. BERT

AU - Tran, Linh

AU - Velazquez, Erick

AU - Sips, Robert Jan

AU - de Boer, Victor

N1 - Copyright: This record is sourced from MEDLINE/PubMed, a database of the U.S. National Library of Medicine

PY - 2021

Y1 - 2021

N2 - Lexical simplification (LS) can decrease the communication gap between medical experts and laypeople by replacing medical terms with layperson counterparts. In this paper, we present: 1) a rule-based approach to LS using a consumer health vocabulary, and 2) an unsupervised approach using BERT to generate word candidates. Human evaluation shows that the unsupervised model performed better for simplicity and grammaticality, while the rule-based method was better at meaning preservation.

AB - Lexical simplification (LS) can decrease the communication gap between medical experts and laypeople by replacing medical terms with layperson counterparts. In this paper, we present: 1) a rule-based approach to LS using a consumer health vocabulary, and 2) an unsupervised approach using BERT to generate word candidates. Human evaluation shows that the unsupervised model performed better for simplicity and grammaticality, while the rule-based method was better at meaning preservation.

KW - Health Vocabulary

KW - Lexical Simplification

KW - Machine Learning

UR - http://www.scopus.com/inward/record.url?scp=85107238009&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85107238009&partnerID=8YFLogxK

U2 - 10.3233/SHTI210337

DO - 10.3233/SHTI210337

M3 - Chapter

C2 - 34042832

AN - SCOPUS:85107238009

SN - 9781643681849

T3 - Studies in health technology and informatics

SP - 1023

EP - 1024

BT - Public Health and Informatics

A2 - Mantas, Jan

PB - IOS Press

ER -

Evaluating Medical Lexical Simplification: Rule-Based vs. BERT

Abstract

Publication series

Bibliographical note

Keywords

Access to Document

Persistent URL (handle)

Other files and links

Fingerprint

Cite this