@inproceedings{pasqualini-etal-2026-novo,
title = "Novo {C}or{P}op Sa{\'u}de: Data Collection for Simplified Health Communication in a {B}razilian Patient Information Leaflet Corpus",
author = "Pasqualini, Bianca and
Finatto, Maria J. B. and
Bertotto, Eduarda and
Carpio, Paula Salem and
Grandi, Roges Horacio and
Wives, Leandro Krug",
editor = "Barbosa, Bryan Khelven da Silva and
Paes, Aline and
Felippo, Ariani Di",
booktitle = "Proceedings of the 17th {B}razilian Symposium in Information and Human Language Technology",
month = oct,
year = "2026",
address = "Cuiab{\'a}, Mato Grosso, Brazil",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.stil-1.25/",
doi = "10.5753/stil.2026.26518",
pages = "297--304",
abstract = "This paper presents exploratory results from the ``Novo CorPop Sa{\'u}de'' project, evaluating whether validation by expert linguists improves readability levels compared to AI-generated simplifications. We analyzed original, AI-generated, and human-validated versions of thirty Patient Information leaflets. Using the Flesch Reading Ease Index, two adapted Dale-Chall metrics, and lexicometric analysis, we assessed automatic simplification against human strategies. Results indicate that while AI improves readability scores primarily through text compression, expert linguists prioritize elaborative strategies, maintaining key terminology while providing didactic explanations to fill semantic gaps. This suggests that human intervention plays a key role in balancing terminological precision with communicative accessibility, a nuance that purely reductive AI strategies might overlook. This study provided evidence on the use of the complex and simplified lexical repertoire of medicine leaflets for the ``Novo CorPop Sa{\'u}de''."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="pasqualini-etal-2026-novo">
<titleInfo>
<title>Novo CorPop Saúde: Data Collection for Simplified Health Communication in a Brazilian Patient Information Leaflet Corpus</title>
</titleInfo>
<name type="personal">
<namePart type="given">Bianca</namePart>
<namePart type="family">Pasqualini</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maria</namePart>
<namePart type="given">J</namePart>
<namePart type="given">B</namePart>
<namePart type="family">Finatto</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eduarda</namePart>
<namePart type="family">Bertotto</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Paula</namePart>
<namePart type="given">Salem</namePart>
<namePart type="family">Carpio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Roges</namePart>
<namePart type="given">Horacio</namePart>
<namePart type="family">Grandi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Leandro</namePart>
<namePart type="given">Krug</namePart>
<namePart type="family">Wives</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 17th Brazilian Symposium in Information and Human Language Technology</title>
</titleInfo>
<name type="personal">
<namePart type="given">Bryan</namePart>
<namePart type="given">Khelven</namePart>
<namePart type="given">da</namePart>
<namePart type="given">Silva</namePart>
<namePart type="family">Barbosa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aline</namePart>
<namePart type="family">Paes</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ariani</namePart>
<namePart type="given">Di</namePart>
<namePart type="family">Felippo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Cuiabá, Mato Grosso, Brazil</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper presents exploratory results from the “Novo CorPop Saúde” project, evaluating whether validation by expert linguists improves readability levels compared to AI-generated simplifications. We analyzed original, AI-generated, and human-validated versions of thirty Patient Information leaflets. Using the Flesch Reading Ease Index, two adapted Dale-Chall metrics, and lexicometric analysis, we assessed automatic simplification against human strategies. Results indicate that while AI improves readability scores primarily through text compression, expert linguists prioritize elaborative strategies, maintaining key terminology while providing didactic explanations to fill semantic gaps. This suggests that human intervention plays a key role in balancing terminological precision with communicative accessibility, a nuance that purely reductive AI strategies might overlook. This study provided evidence on the use of the complex and simplified lexical repertoire of medicine leaflets for the “Novo CorPop Saúde”.</abstract>
<identifier type="citekey">pasqualini-etal-2026-novo</identifier>
<identifier type="doi">10.5753/stil.2026.26518</identifier>
<location>
<url>https://aclanthology.org/2026.stil-1.25/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>297</start>
<end>304</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Novo CorPop Saúde: Data Collection for Simplified Health Communication in a Brazilian Patient Information Leaflet Corpus
%A Pasqualini, Bianca
%A Finatto, Maria J. B.
%A Bertotto, Eduarda
%A Carpio, Paula Salem
%A Grandi, Roges Horacio
%A Wives, Leandro Krug
%Y Barbosa, Bryan Khelven da Silva
%Y Paes, Aline
%Y Felippo, Ariani Di
%S Proceedings of the 17th Brazilian Symposium in Information and Human Language Technology
%D 2026
%8 October
%I Association for Computational Linguistics
%C Cuiabá, Mato Grosso, Brazil
%F pasqualini-etal-2026-novo
%X This paper presents exploratory results from the “Novo CorPop Saúde” project, evaluating whether validation by expert linguists improves readability levels compared to AI-generated simplifications. We analyzed original, AI-generated, and human-validated versions of thirty Patient Information leaflets. Using the Flesch Reading Ease Index, two adapted Dale-Chall metrics, and lexicometric analysis, we assessed automatic simplification against human strategies. Results indicate that while AI improves readability scores primarily through text compression, expert linguists prioritize elaborative strategies, maintaining key terminology while providing didactic explanations to fill semantic gaps. This suggests that human intervention plays a key role in balancing terminological precision with communicative accessibility, a nuance that purely reductive AI strategies might overlook. This study provided evidence on the use of the complex and simplified lexical repertoire of medicine leaflets for the “Novo CorPop Saúde”.
%R 10.5753/stil.2026.26518
%U https://aclanthology.org/2026.stil-1.25/
%U https://doi.org/10.5753/stil.2026.26518
%P 297-304
Markdown (Informal)
[Novo CorPop Saúde: Data Collection for Simplified Health Communication in a Brazilian Patient Information Leaflet Corpus](https://aclanthology.org/2026.stil-1.25/) (Pasqualini et al., STIL 2026)
ACL