@inproceedings{leuzinger-etal-2026-valic,
title = "Valic{\textschwa}: A gender-neutralized dataset of learner {I}talian",
author = {Leuzinger, C{\'e}line and
Grand-Clement, Caroline and
Mu{\~n}oz S{\'a}nchez, Ricardo and
S{\"o}dahl Bladsj{\"o}, Tom},
editor = "Fale{\'n}ska, Agnieszka and
Basta, Christine and
Costa-juss{\`a}, Marta and
Sta{\'n}czak, Karolina and
Nozza, Debora and
Attanasio, Giuseppe and
Neplenbroek, Vera and
Hardmeier, Christian",
booktitle = "Proceedings of the 7th Workshop on Gender Bias in Natural Language Processing ({G}e{BNLP})",
month = nov,
year = "2026",
address = "Hengqin, China (remote)",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.gebnlp-1.2/",
pages = "7--20",
ISBN = "979-8-89176-447-7",
abstract = "Investigations of gender-neutral and non-binary language in Romance languages often fail to take into account learner language. There is a lack of material to study how grammatical error correction models handle non-binary language which uses new forms or morphemes. In this paper, we offer Valic{\textschwa} a gender-neutralized version of the Valico treebank, containing Italian learner texts and their corrections. We present the procedure to gender-neutralize Italian sentences, both grammatically correct and incorrect. We implement two different systems to identify which tokens should be neutralized: a rule-based system and a machine learning system, both of which prove equally efficient. The token swap is rule-based, using the neomorphemes -{\textschwa} and -ɜ to signal singular and plural gender-neutrality. The Valic{\textschwa} dataset can be used to evaluate or train language learning applications for learners of Italian."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="leuzinger-etal-2026-valic">
<titleInfo>
<title>Valic\textschwa: A gender-neutralized dataset of learner Italian</title>
</titleInfo>
<name type="personal">
<namePart type="given">Céline</namePart>
<namePart type="family">Leuzinger</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Caroline</namePart>
<namePart type="family">Grand-Clement</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ricardo</namePart>
<namePart type="family">Muñoz Sánchez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tom</namePart>
<namePart type="family">Södahl Bladsjö</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 7th Workshop on Gender Bias in Natural Language Processing (GeBNLP)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Agnieszka</namePart>
<namePart type="family">Faleńska</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christine</namePart>
<namePart type="family">Basta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marta</namePart>
<namePart type="family">Costa-jussà</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Karolina</namePart>
<namePart type="family">Stańczak</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Debora</namePart>
<namePart type="family">Nozza</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Giuseppe</namePart>
<namePart type="family">Attanasio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vera</namePart>
<namePart type="family">Neplenbroek</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christian</namePart>
<namePart type="family">Hardmeier</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Hengqin, China (remote)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-447-7</identifier>
</relatedItem>
<abstract>Investigations of gender-neutral and non-binary language in Romance languages often fail to take into account learner language. There is a lack of material to study how grammatical error correction models handle non-binary language which uses new forms or morphemes. In this paper, we offer Valic\textschwa a gender-neutralized version of the Valico treebank, containing Italian learner texts and their corrections. We present the procedure to gender-neutralize Italian sentences, both grammatically correct and incorrect. We implement two different systems to identify which tokens should be neutralized: a rule-based system and a machine learning system, both of which prove equally efficient. The token swap is rule-based, using the neomorphemes -\textschwa and -ɜ to signal singular and plural gender-neutrality. The Valic\textschwa dataset can be used to evaluate or train language learning applications for learners of Italian.</abstract>
<identifier type="citekey">leuzinger-etal-2026-valic</identifier>
<location>
<url>https://aclanthology.org/2026.gebnlp-1.2/</url>
</location>
<part>
<date>2026-11</date>
<extent unit="page">
<start>7</start>
<end>20</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Valic\textschwa: A gender-neutralized dataset of learner Italian
%A Leuzinger, Céline
%A Grand-Clement, Caroline
%A Muñoz Sánchez, Ricardo
%A Södahl Bladsjö, Tom
%Y Faleńska, Agnieszka
%Y Basta, Christine
%Y Costa-jussà, Marta
%Y Stańczak, Karolina
%Y Nozza, Debora
%Y Attanasio, Giuseppe
%Y Neplenbroek, Vera
%Y Hardmeier, Christian
%S Proceedings of the 7th Workshop on Gender Bias in Natural Language Processing (GeBNLP)
%D 2026
%8 November
%I Association for Computational Linguistics
%C Hengqin, China (remote)
%@ 979-8-89176-447-7
%F leuzinger-etal-2026-valic
%X Investigations of gender-neutral and non-binary language in Romance languages often fail to take into account learner language. There is a lack of material to study how grammatical error correction models handle non-binary language which uses new forms or morphemes. In this paper, we offer Valic\textschwa a gender-neutralized version of the Valico treebank, containing Italian learner texts and their corrections. We present the procedure to gender-neutralize Italian sentences, both grammatically correct and incorrect. We implement two different systems to identify which tokens should be neutralized: a rule-based system and a machine learning system, both of which prove equally efficient. The token swap is rule-based, using the neomorphemes -\textschwa and -ɜ to signal singular and plural gender-neutrality. The Valic\textschwa dataset can be used to evaluate or train language learning applications for learners of Italian.
%U https://aclanthology.org/2026.gebnlp-1.2/
%P 7-20
Markdown (Informal)
[Valicə: A gender-neutralized dataset of learner Italian](https://aclanthology.org/2026.gebnlp-1.2/) (Leuzinger et al., GeBNLP 2026)
ACL
- Céline Leuzinger, Caroline Grand-Clement, Ricardo Muñoz Sánchez, and Tom Södahl Bladsjö. 2026. Valicə: A gender-neutralized dataset of learner Italian. In Proceedings of the 7th Workshop on Gender Bias in Natural Language Processing (GeBNLP), pages 7–20, Hengqin, China (remote). Association for Computational Linguistics.