@inproceedings{lyu-pergola-2024-scigispy,
title = "{S}ci{G}is{P}y: a Novel Metric for Biomedical Text Simplification via Gist Inference Score",
author = "Lyu, Chen and
Pergola, Gabriele",
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-1.10",
pages = "95--106",
abstract = "Biomedical literature is often written in highly specialized language, posing significant comprehension challenges for non-experts. Automatic text simplification (ATS) offers a solution by making such texts more accessible while preserving critical information. However, evaluating ATS for biomedical texts is still challenging due to the limitations of existing evaluation metrics. General-domain metrics like SARI, BLEU, and ROUGE focus on surface-level text features, and readability metrics like FKGL and ARI fail to account for domain-specific terminology or assess how well the simplified text conveys core meanings (gist). To address this, we introduce SciGisPy, a novel evaluation metric inspired by Gist Inference Score (GIS) from Fuzzy-Trace Theory (FTT). SciGisPy measures how well a simplified text facilitates the formation of abstract inferences (gist) necessary for comprehension, especially in the biomedical domain. We revise GIS for this purpose by introducing domain-specific enhancements, including semantic chunking, Information Content (IC) theory, and specialized embeddings, while removing unsuitable indexes. Our experimental evaluation on the Cochrane biomedical text simplification dataset demonstrates that SciGisPy outperforms the original GIS formulation, with a significant increase in correctly identified simplified texts (84{\%} versus 44.8{\%}). The results and a thorough ablation study confirm that SciGisPy better captures the essential meaning of biomedical content, outperforming existing approaches.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="lyu-pergola-2024-scigispy">
<titleInfo>
<title>SciGisPy: a Novel Metric for Biomedical Text Simplification via Gist Inference Score</title>
</titleInfo>
<name type="personal">
<namePart type="given">Chen</namePart>
<namePart type="family">Lyu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gabriele</namePart>
<namePart type="family">Pergola</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>Biomedical literature is often written in highly specialized language, posing significant comprehension challenges for non-experts. Automatic text simplification (ATS) offers a solution by making such texts more accessible while preserving critical information. However, evaluating ATS for biomedical texts is still challenging due to the limitations of existing evaluation metrics. General-domain metrics like SARI, BLEU, and ROUGE focus on surface-level text features, and readability metrics like FKGL and ARI fail to account for domain-specific terminology or assess how well the simplified text conveys core meanings (gist). To address this, we introduce SciGisPy, a novel evaluation metric inspired by Gist Inference Score (GIS) from Fuzzy-Trace Theory (FTT). SciGisPy measures how well a simplified text facilitates the formation of abstract inferences (gist) necessary for comprehension, especially in the biomedical domain. We revise GIS for this purpose by introducing domain-specific enhancements, including semantic chunking, Information Content (IC) theory, and specialized embeddings, while removing unsuitable indexes. Our experimental evaluation on the Cochrane biomedical text simplification dataset demonstrates that SciGisPy outperforms the original GIS formulation, with a significant increase in correctly identified simplified texts (84% versus 44.8%). The results and a thorough ablation study confirm that SciGisPy better captures the essential meaning of biomedical content, outperforming existing approaches.</abstract>
<identifier type="citekey">lyu-pergola-2024-scigispy</identifier>
<location>
<url>https://aclanthology.org/2024.tsar-1.10</url>
</location>
<part>
<date>2024-11</date>
<extent unit="page">
<start>95</start>
<end>106</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T SciGisPy: a Novel Metric for Biomedical Text Simplification via Gist Inference Score
%A Lyu, Chen
%A Pergola, Gabriele
%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 lyu-pergola-2024-scigispy
%X Biomedical literature is often written in highly specialized language, posing significant comprehension challenges for non-experts. Automatic text simplification (ATS) offers a solution by making such texts more accessible while preserving critical information. However, evaluating ATS for biomedical texts is still challenging due to the limitations of existing evaluation metrics. General-domain metrics like SARI, BLEU, and ROUGE focus on surface-level text features, and readability metrics like FKGL and ARI fail to account for domain-specific terminology or assess how well the simplified text conveys core meanings (gist). To address this, we introduce SciGisPy, a novel evaluation metric inspired by Gist Inference Score (GIS) from Fuzzy-Trace Theory (FTT). SciGisPy measures how well a simplified text facilitates the formation of abstract inferences (gist) necessary for comprehension, especially in the biomedical domain. We revise GIS for this purpose by introducing domain-specific enhancements, including semantic chunking, Information Content (IC) theory, and specialized embeddings, while removing unsuitable indexes. Our experimental evaluation on the Cochrane biomedical text simplification dataset demonstrates that SciGisPy outperforms the original GIS formulation, with a significant increase in correctly identified simplified texts (84% versus 44.8%). The results and a thorough ablation study confirm that SciGisPy better captures the essential meaning of biomedical content, outperforming existing approaches.
%U https://aclanthology.org/2024.tsar-1.10
%P 95-106
Markdown (Informal)
[SciGisPy: a Novel Metric for Biomedical Text Simplification via Gist Inference Score](https://aclanthology.org/2024.tsar-1.10) (Lyu & Pergola, TSAR 2024)
ACL