@inproceedings{jiang-xu-2024-medreadme,
title = "{M}ed{R}ead{M}e: A Systematic Study for Fine-grained Sentence Readability in Medical Domain",
author = "Jiang, Chao and
Xu, Wei",
editor = "Al-Onaizan, Yaser and
Bansal, Mohit and
Chen, Yun-Nung",
booktitle = "Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing",
month = nov,
year = "2024",
address = "Miami, Florida, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.emnlp-main.958/",
doi = "10.18653/v1/2024.emnlp-main.958",
pages = "17293--17319",
abstract = "Medical texts are notoriously challenging to read. Properly measuring their readability is the first step towards making them more accessible. Here, we present the first systematic study on fine-grained readability measurements in the medical domain, at both sentence-level and span-level. We first introduce a new dataset MedReadMe, which consists of manually annotated readability ratings and fine-grained complex span annotation for 4,520 sentences, featuring two novel {\textquotedblleft}Google-Easy{\textquotedblright} and {\textquotedblleft}Google-Hard{\textquotedblright} categories. It supports our quantitative analysis, which covers 650 linguistic features and additional complex span features, to answer {\textquotedblleft}why medical sentences are so hard.{\textquotedblright} Enabled by our high-quality annotation, we benchmark several state-of-the-art sentence-level readability metrics, including unsupervised, supervised, and prompting-based methods using recently developed large language models (LLMs). Informed by our fine-grained complex span annotation, we find that adding a single feature, capturing the number of jargon spans, into existing readability formulas can significantly improve their correlation with human judgments, and also make them more stable. We will publicly release data and code."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="jiang-xu-2024-medreadme">
<titleInfo>
<title>MedReadMe: A Systematic Study for Fine-grained Sentence Readability in Medical Domain</title>
</titleInfo>
<name type="personal">
<namePart type="given">Chao</namePart>
<namePart type="family">Jiang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wei</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yaser</namePart>
<namePart type="family">Al-Onaizan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohit</namePart>
<namePart type="family">Bansal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yun-Nung</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Miami, Florida, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Medical texts are notoriously challenging to read. Properly measuring their readability is the first step towards making them more accessible. Here, we present the first systematic study on fine-grained readability measurements in the medical domain, at both sentence-level and span-level. We first introduce a new dataset MedReadMe, which consists of manually annotated readability ratings and fine-grained complex span annotation for 4,520 sentences, featuring two novel “Google-Easy” and “Google-Hard” categories. It supports our quantitative analysis, which covers 650 linguistic features and additional complex span features, to answer “why medical sentences are so hard.” Enabled by our high-quality annotation, we benchmark several state-of-the-art sentence-level readability metrics, including unsupervised, supervised, and prompting-based methods using recently developed large language models (LLMs). Informed by our fine-grained complex span annotation, we find that adding a single feature, capturing the number of jargon spans, into existing readability formulas can significantly improve their correlation with human judgments, and also make them more stable. We will publicly release data and code.</abstract>
<identifier type="citekey">jiang-xu-2024-medreadme</identifier>
<identifier type="doi">10.18653/v1/2024.emnlp-main.958</identifier>
<location>
<url>https://aclanthology.org/2024.emnlp-main.958/</url>
</location>
<part>
<date>2024-11</date>
<extent unit="page">
<start>17293</start>
<end>17319</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T MedReadMe: A Systematic Study for Fine-grained Sentence Readability in Medical Domain
%A Jiang, Chao
%A Xu, Wei
%Y Al-Onaizan, Yaser
%Y Bansal, Mohit
%Y Chen, Yun-Nung
%S Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing
%D 2024
%8 November
%I Association for Computational Linguistics
%C Miami, Florida, USA
%F jiang-xu-2024-medreadme
%X Medical texts are notoriously challenging to read. Properly measuring their readability is the first step towards making them more accessible. Here, we present the first systematic study on fine-grained readability measurements in the medical domain, at both sentence-level and span-level. We first introduce a new dataset MedReadMe, which consists of manually annotated readability ratings and fine-grained complex span annotation for 4,520 sentences, featuring two novel “Google-Easy” and “Google-Hard” categories. It supports our quantitative analysis, which covers 650 linguistic features and additional complex span features, to answer “why medical sentences are so hard.” Enabled by our high-quality annotation, we benchmark several state-of-the-art sentence-level readability metrics, including unsupervised, supervised, and prompting-based methods using recently developed large language models (LLMs). Informed by our fine-grained complex span annotation, we find that adding a single feature, capturing the number of jargon spans, into existing readability formulas can significantly improve their correlation with human judgments, and also make them more stable. We will publicly release data and code.
%R 10.18653/v1/2024.emnlp-main.958
%U https://aclanthology.org/2024.emnlp-main.958/
%U https://doi.org/10.18653/v1/2024.emnlp-main.958
%P 17293-17319
Markdown (Informal)
[MedReadMe: A Systematic Study for Fine-grained Sentence Readability in Medical Domain](https://aclanthology.org/2024.emnlp-main.958/) (Jiang & Xu, EMNLP 2024)
ACL