@inproceedings{horiguchi-etal-2024-evaluation,
title = "Evaluation Dataset for {J}apanese Medical Text Simplification",
author = "Horiguchi, Koki and
Kajiwara, Tomoyuki and
Arase, Yuki and
Ninomiya, Takashi",
editor = "Cao, Yang (Trista) and
Papadimitriou, Isabel and
Ovalle, Anaelia",
booktitle = "Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 4: Student Research Workshop)",
month = jun,
year = "2024",
address = "Mexico City, Mexico",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.naacl-srw.23",
pages = "219--225",
abstract = "We create a parallel corpus for medical text simplification in Japanese, which simplifies medical terms into expressions that patients can understand without effort.While text simplification in the medial domain is strongly desired by society, it is less explored in Japanese because of the lack of language resources.In this study, we build a parallel corpus for Japanese text simplification evaluation in the medical domain using patients{'} weblogs.This corpus consists of 1,425 pairs of complex and simple sentences with or without medical terms.To tackle medical text simplification without a training corpus of the corresponding domain, we repurpose a Japanese text simplification model of other domains.Furthermore, we propose a lexically constrained reranking method that allows to avoid technical terms to be output.Experimental results show that our method contributes to achieving higher simplification performance in the medical domain.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="horiguchi-etal-2024-evaluation">
<titleInfo>
<title>Evaluation Dataset for Japanese Medical Text Simplification</title>
</titleInfo>
<name type="personal">
<namePart type="given">Koki</namePart>
<namePart type="family">Horiguchi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tomoyuki</namePart>
<namePart type="family">Kajiwara</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuki</namePart>
<namePart type="family">Arase</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Takashi</namePart>
<namePart type="family">Ninomiya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 4: Student Research Workshop)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yang</namePart>
<namePart type="given">(Trista)</namePart>
<namePart type="family">Cao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Isabel</namePart>
<namePart type="family">Papadimitriou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anaelia</namePart>
<namePart type="family">Ovalle</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Mexico City, Mexico</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We create a parallel corpus for medical text simplification in Japanese, which simplifies medical terms into expressions that patients can understand without effort.While text simplification in the medial domain is strongly desired by society, it is less explored in Japanese because of the lack of language resources.In this study, we build a parallel corpus for Japanese text simplification evaluation in the medical domain using patients’ weblogs.This corpus consists of 1,425 pairs of complex and simple sentences with or without medical terms.To tackle medical text simplification without a training corpus of the corresponding domain, we repurpose a Japanese text simplification model of other domains.Furthermore, we propose a lexically constrained reranking method that allows to avoid technical terms to be output.Experimental results show that our method contributes to achieving higher simplification performance in the medical domain.</abstract>
<identifier type="citekey">horiguchi-etal-2024-evaluation</identifier>
<location>
<url>https://aclanthology.org/2024.naacl-srw.23</url>
</location>
<part>
<date>2024-06</date>
<extent unit="page">
<start>219</start>
<end>225</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Evaluation Dataset for Japanese Medical Text Simplification
%A Horiguchi, Koki
%A Kajiwara, Tomoyuki
%A Arase, Yuki
%A Ninomiya, Takashi
%Y Cao, Yang (Trista)
%Y Papadimitriou, Isabel
%Y Ovalle, Anaelia
%S Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 4: Student Research Workshop)
%D 2024
%8 June
%I Association for Computational Linguistics
%C Mexico City, Mexico
%F horiguchi-etal-2024-evaluation
%X We create a parallel corpus for medical text simplification in Japanese, which simplifies medical terms into expressions that patients can understand without effort.While text simplification in the medial domain is strongly desired by society, it is less explored in Japanese because of the lack of language resources.In this study, we build a parallel corpus for Japanese text simplification evaluation in the medical domain using patients’ weblogs.This corpus consists of 1,425 pairs of complex and simple sentences with or without medical terms.To tackle medical text simplification without a training corpus of the corresponding domain, we repurpose a Japanese text simplification model of other domains.Furthermore, we propose a lexically constrained reranking method that allows to avoid technical terms to be output.Experimental results show that our method contributes to achieving higher simplification performance in the medical domain.
%U https://aclanthology.org/2024.naacl-srw.23
%P 219-225
Markdown (Informal)
[Evaluation Dataset for Japanese Medical Text Simplification](https://aclanthology.org/2024.naacl-srw.23) (Horiguchi et al., NAACL 2024)
ACL
- Koki Horiguchi, Tomoyuki Kajiwara, Yuki Arase, and Takashi Ninomiya. 2024. Evaluation Dataset for Japanese Medical Text Simplification. In Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 4: Student Research Workshop), pages 219–225, Mexico City, Mexico. Association for Computational Linguistics.