@inproceedings{schoffen-etal-2026-corspell,
title = "{C}or{S}pell: Introducing a Semiautomatic Tool for Spelling Normalization in {B}razilian {P}ortuguese",
author = "Schoffen, Juliana and
Balreira, Dennis Giovani and
Stumpf, Elisa Marchioro and
Goulart, Larissa and
Zingano Kuhn, Tanara and
Nunes, Rafael Oleques and
Ricci Pazzinato, Gabriel and
Dahmer Hanauer, Isadora and
de Souza Silva, Jos{\'e} Henrique and
Sarmento Divino, Luiza and
Matte, Marine",
editor = "Piperidis, Stelios and
Bel, N{\'u}ria and
van den Heuvel, Henk and
Ide, Nancy and
Krek, Simon and
Toral, Antonio",
booktitle = "Proceedings of the Fifteenth Language Resources and Evaluation Conference",
month = may,
year = "2026",
address = "Palma de Mallorca, Spain",
publisher = "ELRA Language Resource Association",
url = "https://aclanthology.org/2026.lrec-1.130/",
doi = "10.63317/22uey2oj2w49",
pages = "1659--1667",
abstract = "With the growing availability of large text collections, efficient tools for corpus annotation and normalization have become increasingly important in linguistic and computational research. This paper presents CorSpell, a semiautomatic tool developed to support the spelling normalization of Brazilian Portuguese texts within the CorCel project{---}a corpus comprising over 15,000 handwritten exam responses from the Celpe-Bras proficiency test. Given the corpus scale, manual normalization is impractical; CorSpell streamlines this process by enabling users to visualize, select, and replace tokens directly through an intuitive web interface. The tool integrates automatic suggestions from PT-BR dictionaries with human validation, providing an interface for users to access and manipulate the texts. CorSpell significantly reduces annotation time, minimizes errors, and facilitates collaborative work, providing a practical and scalable solution for corpus normalization and a foundation for LLM-based modeling of Portuguese proficiency."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="schoffen-etal-2026-corspell">
<titleInfo>
<title>CorSpell: Introducing a Semiautomatic Tool for Spelling Normalization in Brazilian Portuguese</title>
</titleInfo>
<name type="personal">
<namePart type="given">Juliana</namePart>
<namePart type="family">Schoffen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dennis</namePart>
<namePart type="given">Giovani</namePart>
<namePart type="family">Balreira</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Elisa</namePart>
<namePart type="given">Marchioro</namePart>
<namePart type="family">Stumpf</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Larissa</namePart>
<namePart type="family">Goulart</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tanara</namePart>
<namePart type="family">Zingano Kuhn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rafael</namePart>
<namePart type="given">Oleques</namePart>
<namePart type="family">Nunes</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gabriel</namePart>
<namePart type="family">Ricci Pazzinato</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Isadora</namePart>
<namePart type="family">Dahmer Hanauer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">José</namePart>
<namePart type="given">Henrique</namePart>
<namePart type="family">de Souza Silva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Luiza</namePart>
<namePart type="family">Sarmento Divino</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marine</namePart>
<namePart type="family">Matte</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fifteenth Language Resources and Evaluation Conference</title>
</titleInfo>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Núria</namePart>
<namePart type="family">Bel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Henk</namePart>
<namePart type="family">van den Heuvel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nancy</namePart>
<namePart type="family">Ide</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Simon</namePart>
<namePart type="family">Krek</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Antonio</namePart>
<namePart type="family">Toral</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA Language Resource Association</publisher>
<place>
<placeTerm type="text">Palma de Mallorca, Spain</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>With the growing availability of large text collections, efficient tools for corpus annotation and normalization have become increasingly important in linguistic and computational research. This paper presents CorSpell, a semiautomatic tool developed to support the spelling normalization of Brazilian Portuguese texts within the CorCel project—a corpus comprising over 15,000 handwritten exam responses from the Celpe-Bras proficiency test. Given the corpus scale, manual normalization is impractical; CorSpell streamlines this process by enabling users to visualize, select, and replace tokens directly through an intuitive web interface. The tool integrates automatic suggestions from PT-BR dictionaries with human validation, providing an interface for users to access and manipulate the texts. CorSpell significantly reduces annotation time, minimizes errors, and facilitates collaborative work, providing a practical and scalable solution for corpus normalization and a foundation for LLM-based modeling of Portuguese proficiency.</abstract>
<identifier type="citekey">schoffen-etal-2026-corspell</identifier>
<identifier type="doi">10.63317/22uey2oj2w49</identifier>
<location>
<url>https://aclanthology.org/2026.lrec-1.130/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>1659</start>
<end>1667</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T CorSpell: Introducing a Semiautomatic Tool for Spelling Normalization in Brazilian Portuguese
%A Schoffen, Juliana
%A Balreira, Dennis Giovani
%A Stumpf, Elisa Marchioro
%A Goulart, Larissa
%A Zingano Kuhn, Tanara
%A Nunes, Rafael Oleques
%A Ricci Pazzinato, Gabriel
%A Dahmer Hanauer, Isadora
%A de Souza Silva, José Henrique
%A Sarmento Divino, Luiza
%A Matte, Marine
%Y Piperidis, Stelios
%Y Bel, Núria
%Y van den Heuvel, Henk
%Y Ide, Nancy
%Y Krek, Simon
%Y Toral, Antonio
%S Proceedings of the Fifteenth Language Resources and Evaluation Conference
%D 2026
%8 May
%I ELRA Language Resource Association
%C Palma de Mallorca, Spain
%F schoffen-etal-2026-corspell
%X With the growing availability of large text collections, efficient tools for corpus annotation and normalization have become increasingly important in linguistic and computational research. This paper presents CorSpell, a semiautomatic tool developed to support the spelling normalization of Brazilian Portuguese texts within the CorCel project—a corpus comprising over 15,000 handwritten exam responses from the Celpe-Bras proficiency test. Given the corpus scale, manual normalization is impractical; CorSpell streamlines this process by enabling users to visualize, select, and replace tokens directly through an intuitive web interface. The tool integrates automatic suggestions from PT-BR dictionaries with human validation, providing an interface for users to access and manipulate the texts. CorSpell significantly reduces annotation time, minimizes errors, and facilitates collaborative work, providing a practical and scalable solution for corpus normalization and a foundation for LLM-based modeling of Portuguese proficiency.
%R 10.63317/22uey2oj2w49
%U https://aclanthology.org/2026.lrec-1.130/
%U https://doi.org/10.63317/22uey2oj2w49
%P 1659-1667
Markdown (Informal)
[CorSpell: Introducing a Semiautomatic Tool for Spelling Normalization in Brazilian Portuguese](https://aclanthology.org/2026.lrec-1.130/) (Schoffen et al., LREC 2026)
ACL
- Juliana Schoffen, Dennis Giovani Balreira, Elisa Marchioro Stumpf, Larissa Goulart, Tanara Zingano Kuhn, Rafael Oleques Nunes, Gabriel Ricci Pazzinato, Isadora Dahmer Hanauer, José Henrique de Souza Silva, Luiza Sarmento Divino, and Marine Matte. 2026. CorSpell: Introducing a Semiautomatic Tool for Spelling Normalization in Brazilian Portuguese. In Proceedings of the Fifteenth Language Resources and Evaluation Conference, pages 1659–1667, Palma de Mallorca, Spain. ELRA Language Resource Association.