@inproceedings{luo-etal-2022-benchmarking,
title = "Benchmarking Automated Clinical Language Simplification: Dataset, Algorithm, and Evaluation",
author = "Luo, Junyu and
Lin, Junxian and
Lin, Chi and
Xiao, Cao and
Gui, Xinning and
Ma, Fenglong",
editor = "Calzolari, Nicoletta and
Huang, Chu-Ren and
Kim, Hansaem and
Pustejovsky, James and
Wanner, Leo and
Choi, Key-Sun and
Ryu, Pum-Mo and
Chen, Hsin-Hsi and
Donatelli, Lucia and
Ji, Heng and
Kurohashi, Sadao and
Paggio, Patrizia and
Xue, Nianwen and
Kim, Seokhwan and
Hahm, Younggyun and
He, Zhong and
Lee, Tony Kyungil and
Santus, Enrico and
Bond, Francis and
Na, Seung-Hoon",
booktitle = "Proceedings of the 29th International Conference on Computational Linguistics",
month = oct,
year = "2022",
address = "Gyeongju, Republic of Korea",
publisher = "International Committee on Computational Linguistics",
url = "https://aclanthology.org/2022.coling-1.313/",
pages = "3550--3562",
abstract = "Patients with low health literacy usually have difficulty understanding medical jargon and the complex structure of professional medical language. Although some studies are proposed to automatically translate expert language into layperson-understandable language, only a few of them focus on both accuracy and readability aspects simultaneously in the clinical domain. Thus, simplification of the clinical language is still a challenging task, but unfortunately, it is not yet fully addressed in previous work. To benchmark this task, we construct a new dataset named MedLane to support the development and evaluation of automated clinical language simplification approaches. Besides, we propose a new model called DECLARE that follows the human annotation procedure and achieves state-of-the-art performance compared with eight strong baselines. To fairly evaluate the performance, we also propose three specific evaluation metrics. Experimental results demonstrate the utility of the annotated MedLane dataset and the effectiveness of the proposed model DECLARE."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="luo-etal-2022-benchmarking">
<titleInfo>
<title>Benchmarking Automated Clinical Language Simplification: Dataset, Algorithm, and Evaluation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Junyu</namePart>
<namePart type="family">Luo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Junxian</namePart>
<namePart type="family">Lin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chi</namePart>
<namePart type="family">Lin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Cao</namePart>
<namePart type="family">Xiao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xinning</namePart>
<namePart type="family">Gui</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fenglong</namePart>
<namePart type="family">Ma</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 29th International Conference on Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chu-Ren</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hansaem</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">James</namePart>
<namePart type="family">Pustejovsky</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Leo</namePart>
<namePart type="family">Wanner</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Key-Sun</namePart>
<namePart type="family">Choi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pum-Mo</namePart>
<namePart type="family">Ryu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hsin-Hsi</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lucia</namePart>
<namePart type="family">Donatelli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Heng</namePart>
<namePart type="family">Ji</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sadao</namePart>
<namePart type="family">Kurohashi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Patrizia</namePart>
<namePart type="family">Paggio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nianwen</namePart>
<namePart type="family">Xue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Seokhwan</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Younggyun</namePart>
<namePart type="family">Hahm</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhong</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tony</namePart>
<namePart type="given">Kyungil</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Enrico</namePart>
<namePart type="family">Santus</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Francis</namePart>
<namePart type="family">Bond</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Seung-Hoon</namePart>
<namePart type="family">Na</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>International Committee on Computational Linguistics</publisher>
<place>
<placeTerm type="text">Gyeongju, Republic of Korea</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Patients with low health literacy usually have difficulty understanding medical jargon and the complex structure of professional medical language. Although some studies are proposed to automatically translate expert language into layperson-understandable language, only a few of them focus on both accuracy and readability aspects simultaneously in the clinical domain. Thus, simplification of the clinical language is still a challenging task, but unfortunately, it is not yet fully addressed in previous work. To benchmark this task, we construct a new dataset named MedLane to support the development and evaluation of automated clinical language simplification approaches. Besides, we propose a new model called DECLARE that follows the human annotation procedure and achieves state-of-the-art performance compared with eight strong baselines. To fairly evaluate the performance, we also propose three specific evaluation metrics. Experimental results demonstrate the utility of the annotated MedLane dataset and the effectiveness of the proposed model DECLARE.</abstract>
<identifier type="citekey">luo-etal-2022-benchmarking</identifier>
<location>
<url>https://aclanthology.org/2022.coling-1.313/</url>
</location>
<part>
<date>2022-10</date>
<extent unit="page">
<start>3550</start>
<end>3562</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Benchmarking Automated Clinical Language Simplification: Dataset, Algorithm, and Evaluation
%A Luo, Junyu
%A Lin, Junxian
%A Lin, Chi
%A Xiao, Cao
%A Gui, Xinning
%A Ma, Fenglong
%Y Calzolari, Nicoletta
%Y Huang, Chu-Ren
%Y Kim, Hansaem
%Y Pustejovsky, James
%Y Wanner, Leo
%Y Choi, Key-Sun
%Y Ryu, Pum-Mo
%Y Chen, Hsin-Hsi
%Y Donatelli, Lucia
%Y Ji, Heng
%Y Kurohashi, Sadao
%Y Paggio, Patrizia
%Y Xue, Nianwen
%Y Kim, Seokhwan
%Y Hahm, Younggyun
%Y He, Zhong
%Y Lee, Tony Kyungil
%Y Santus, Enrico
%Y Bond, Francis
%Y Na, Seung-Hoon
%S Proceedings of the 29th International Conference on Computational Linguistics
%D 2022
%8 October
%I International Committee on Computational Linguistics
%C Gyeongju, Republic of Korea
%F luo-etal-2022-benchmarking
%X Patients with low health literacy usually have difficulty understanding medical jargon and the complex structure of professional medical language. Although some studies are proposed to automatically translate expert language into layperson-understandable language, only a few of them focus on both accuracy and readability aspects simultaneously in the clinical domain. Thus, simplification of the clinical language is still a challenging task, but unfortunately, it is not yet fully addressed in previous work. To benchmark this task, we construct a new dataset named MedLane to support the development and evaluation of automated clinical language simplification approaches. Besides, we propose a new model called DECLARE that follows the human annotation procedure and achieves state-of-the-art performance compared with eight strong baselines. To fairly evaluate the performance, we also propose three specific evaluation metrics. Experimental results demonstrate the utility of the annotated MedLane dataset and the effectiveness of the proposed model DECLARE.
%U https://aclanthology.org/2022.coling-1.313/
%P 3550-3562
Markdown (Informal)
[Benchmarking Automated Clinical Language Simplification: Dataset, Algorithm, and Evaluation](https://aclanthology.org/2022.coling-1.313/) (Luo et al., COLING 2022)
ACL
- Junyu Luo, Junxian Lin, Chi Lin, Cao Xiao, Xinning Gui, and Fenglong Ma. 2022. Benchmarking Automated Clinical Language Simplification: Dataset, Algorithm, and Evaluation. In Proceedings of the 29th International Conference on Computational Linguistics, pages 3550–3562, Gyeongju, Republic of Korea. International Committee on Computational Linguistics.