@inproceedings{bakker-kamps-2024-cochrane,
title = "Cochrane-auto: An Aligned Dataset for the Simplification of Biomedical Abstracts",
author = "Bakker, Jan and
Kamps, Jaap",
editor = "Shardlow, Matthew and
Saggion, Horacio and
Alva-Manchego, Fernando and
Zampieri, Marcos and
North, Kai and
{\v{S}}tajner, Sanja and
Stodden, Regina",
booktitle = "Proceedings of the Third Workshop on Text Simplification, Accessibility and Readability (TSAR 2024)",
month = nov,
year = "2024",
address = "Miami, Florida, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.tsar-1.5",
doi = "10.18653/v1/2024.tsar-1.5",
pages = "41--51",
abstract = "The most reliable and up-to-date information on health questions is in the biomedical literature, but inaccessible due to the complex language full of jargon. Domain specific scientific text simplification holds the promise to make this literature accessible to a lay audience. Therefore, we create Cochrane-auto: a large corpus of pairs of aligned sentences, paragraphs, and abstracts from biomedical abstracts and lay summaries. Experiments demonstrate that a plan-guided simplification system trained on Cochrane-auto is able to outperform a strong baseline trained on unaligned abstracts and lay summaries. More generally, our freely available corpus complementing Newsela-auto and Wiki-auto facilitates text simplification research beyond the sentence-level and direct lexical and grammatical revisions.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="bakker-kamps-2024-cochrane">
<titleInfo>
<title>Cochrane-auto: An Aligned Dataset for the Simplification of Biomedical Abstracts</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="family">Bakker</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jaap</namePart>
<namePart type="family">Kamps</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 Third Workshop on Text Simplification, Accessibility and Readability (TSAR 2024)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Matthew</namePart>
<namePart type="family">Shardlow</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Horacio</namePart>
<namePart type="family">Saggion</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fernando</namePart>
<namePart type="family">Alva-Manchego</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marcos</namePart>
<namePart type="family">Zampieri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kai</namePart>
<namePart type="family">North</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sanja</namePart>
<namePart type="family">Štajner</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Regina</namePart>
<namePart type="family">Stodden</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>The most reliable and up-to-date information on health questions is in the biomedical literature, but inaccessible due to the complex language full of jargon. Domain specific scientific text simplification holds the promise to make this literature accessible to a lay audience. Therefore, we create Cochrane-auto: a large corpus of pairs of aligned sentences, paragraphs, and abstracts from biomedical abstracts and lay summaries. Experiments demonstrate that a plan-guided simplification system trained on Cochrane-auto is able to outperform a strong baseline trained on unaligned abstracts and lay summaries. More generally, our freely available corpus complementing Newsela-auto and Wiki-auto facilitates text simplification research beyond the sentence-level and direct lexical and grammatical revisions.</abstract>
<identifier type="citekey">bakker-kamps-2024-cochrane</identifier>
<identifier type="doi">10.18653/v1/2024.tsar-1.5</identifier>
<location>
<url>https://aclanthology.org/2024.tsar-1.5</url>
</location>
<part>
<date>2024-11</date>
<extent unit="page">
<start>41</start>
<end>51</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Cochrane-auto: An Aligned Dataset for the Simplification of Biomedical Abstracts
%A Bakker, Jan
%A Kamps, Jaap
%Y Shardlow, Matthew
%Y Saggion, Horacio
%Y Alva-Manchego, Fernando
%Y Zampieri, Marcos
%Y North, Kai
%Y Štajner, Sanja
%Y Stodden, Regina
%S Proceedings of the Third Workshop on Text Simplification, Accessibility and Readability (TSAR 2024)
%D 2024
%8 November
%I Association for Computational Linguistics
%C Miami, Florida, USA
%F bakker-kamps-2024-cochrane
%X The most reliable and up-to-date information on health questions is in the biomedical literature, but inaccessible due to the complex language full of jargon. Domain specific scientific text simplification holds the promise to make this literature accessible to a lay audience. Therefore, we create Cochrane-auto: a large corpus of pairs of aligned sentences, paragraphs, and abstracts from biomedical abstracts and lay summaries. Experiments demonstrate that a plan-guided simplification system trained on Cochrane-auto is able to outperform a strong baseline trained on unaligned abstracts and lay summaries. More generally, our freely available corpus complementing Newsela-auto and Wiki-auto facilitates text simplification research beyond the sentence-level and direct lexical and grammatical revisions.
%R 10.18653/v1/2024.tsar-1.5
%U https://aclanthology.org/2024.tsar-1.5
%U https://doi.org/10.18653/v1/2024.tsar-1.5
%P 41-51
Markdown (Informal)
[Cochrane-auto: An Aligned Dataset for the Simplification of Biomedical Abstracts](https://aclanthology.org/2024.tsar-1.5) (Bakker & Kamps, TSAR 2024)
ACL