@inproceedings{bao-etal-2024-ctyun,
title = "Ctyun {AI} at {B}io{L}ay{S}umm: Enhancing Lay Summaries of Biomedical Articles Through Large Language Models and Data Augmentation",
author = "Bao, Siyu and
Zhao, Ruijing and
Zhang, Siqin and
Zhang, Jinghui and
Wang, Weiyin and
Ru, Yunian",
editor = "Demner-Fushman, Dina and
Ananiadou, Sophia and
Miwa, Makoto and
Roberts, Kirk and
Tsujii, Junichi",
booktitle = "Proceedings of the 23rd Workshop on Biomedical Natural Language Processing",
month = aug,
year = "2024",
address = "Bangkok, Thailand",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.bionlp-1.79",
doi = "10.18653/v1/2024.bionlp-1.79",
pages = "837--844",
abstract = "Lay summaries play a crucial role in making scientific research accessible to a wider audience. However, generating lay summaries from lengthy articles poses significant challenges. We consider two approaches to address this issue: Hard Truncation, which preserves the most informative initial portion of the article, and Text Chunking, which segments articles into smaller, manageable chunks. Our workflow encompasses data preprocessing, augmentation, prompt engineering, and fine-tuning large language models. We explore the influence of pretrained model selection, inference prompt design, and hyperparameter tuning on summarization performance. Our methods demonstrate effectiveness in generating high-quality, informative lay summaries, achieving the second-best performance in the BioLaySumm shared task at BioNLP 2024.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="bao-etal-2024-ctyun">
<titleInfo>
<title>Ctyun AI at BioLaySumm: Enhancing Lay Summaries of Biomedical Articles Through Large Language Models and Data Augmentation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Siyu</namePart>
<namePart type="family">Bao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ruijing</namePart>
<namePart type="family">Zhao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Siqin</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jinghui</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Weiyin</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yunian</namePart>
<namePart type="family">Ru</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 23rd Workshop on Biomedical Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Dina</namePart>
<namePart type="family">Demner-Fushman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sophia</namePart>
<namePart type="family">Ananiadou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Makoto</namePart>
<namePart type="family">Miwa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kirk</namePart>
<namePart type="family">Roberts</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Junichi</namePart>
<namePart type="family">Tsujii</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Bangkok, Thailand</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Lay summaries play a crucial role in making scientific research accessible to a wider audience. However, generating lay summaries from lengthy articles poses significant challenges. We consider two approaches to address this issue: Hard Truncation, which preserves the most informative initial portion of the article, and Text Chunking, which segments articles into smaller, manageable chunks. Our workflow encompasses data preprocessing, augmentation, prompt engineering, and fine-tuning large language models. We explore the influence of pretrained model selection, inference prompt design, and hyperparameter tuning on summarization performance. Our methods demonstrate effectiveness in generating high-quality, informative lay summaries, achieving the second-best performance in the BioLaySumm shared task at BioNLP 2024.</abstract>
<identifier type="citekey">bao-etal-2024-ctyun</identifier>
<identifier type="doi">10.18653/v1/2024.bionlp-1.79</identifier>
<location>
<url>https://aclanthology.org/2024.bionlp-1.79</url>
</location>
<part>
<date>2024-08</date>
<extent unit="page">
<start>837</start>
<end>844</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Ctyun AI at BioLaySumm: Enhancing Lay Summaries of Biomedical Articles Through Large Language Models and Data Augmentation
%A Bao, Siyu
%A Zhao, Ruijing
%A Zhang, Siqin
%A Zhang, Jinghui
%A Wang, Weiyin
%A Ru, Yunian
%Y Demner-Fushman, Dina
%Y Ananiadou, Sophia
%Y Miwa, Makoto
%Y Roberts, Kirk
%Y Tsujii, Junichi
%S Proceedings of the 23rd Workshop on Biomedical Natural Language Processing
%D 2024
%8 August
%I Association for Computational Linguistics
%C Bangkok, Thailand
%F bao-etal-2024-ctyun
%X Lay summaries play a crucial role in making scientific research accessible to a wider audience. However, generating lay summaries from lengthy articles poses significant challenges. We consider two approaches to address this issue: Hard Truncation, which preserves the most informative initial portion of the article, and Text Chunking, which segments articles into smaller, manageable chunks. Our workflow encompasses data preprocessing, augmentation, prompt engineering, and fine-tuning large language models. We explore the influence of pretrained model selection, inference prompt design, and hyperparameter tuning on summarization performance. Our methods demonstrate effectiveness in generating high-quality, informative lay summaries, achieving the second-best performance in the BioLaySumm shared task at BioNLP 2024.
%R 10.18653/v1/2024.bionlp-1.79
%U https://aclanthology.org/2024.bionlp-1.79
%U https://doi.org/10.18653/v1/2024.bionlp-1.79
%P 837-844
Markdown (Informal)
[Ctyun AI at BioLaySumm: Enhancing Lay Summaries of Biomedical Articles Through Large Language Models and Data Augmentation](https://aclanthology.org/2024.bionlp-1.79) (Bao et al., BioNLP-WS 2024)
ACL