@inproceedings{johansson-etal-2026-meta4xnli,
title = "{M}eta4{XNLI}-pt{BR}: {B}razilian {P}ortuguese Extension of {M}eta4{XNLI} Corpus",
author = "Johansson, Karina and
Assi, Fernanda and
da Silva, Isabella and
Passador, Rafael and
Rodrigues, Isabela and
Paes, Aline and
Caseli, Helena",
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-1.131/",
doi = "10.63317/45566xcgz65x",
pages = "1668--1676",
abstract = "Metaphor is a pervasive phenomenon in language that shapes how people conceptualize and communicate complex ideas. Detecting and interpreting metaphor is not only relevant for linguistic theory but also for many Natural Language Processing (NLP) applications, from machine translation to sentiment analysis, to mention a few. Despite its relevance, no open-source annotated corpus of metaphors exists for one of the world{'}s most widely spoken languages: Brazilian Portuguese. This paper addresses this gap by presenting an extension of Meta4XNLI, Meta4XNLI-ptBR, with token-level metaphor annotation in Brazilian Portuguese. To achieve this, we propose a pipeline that combines automatic translation via language models with human annotation, following guidelines adapted from MIPVU and Meta4XNLI. The final corpus contains 1,784 human-annotated sentences, of which 42.26{\%} contain at least one metaphorical token. To our knowledge, this is the first open corpus of its kind for Brazilian Portuguese, and it is already freely available."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="johansson-etal-2026-meta4xnli">
<titleInfo>
<title>Meta4XNLI-ptBR: Brazilian Portuguese Extension of Meta4XNLI Corpus</title>
</titleInfo>
<name type="personal">
<namePart type="given">Karina</namePart>
<namePart type="family">Johansson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fernanda</namePart>
<namePart type="family">Assi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Isabella</namePart>
<namePart type="family">da Silva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rafael</namePart>
<namePart type="family">Passador</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Isabela</namePart>
<namePart type="family">Rodrigues</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aline</namePart>
<namePart type="family">Paes</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Helena</namePart>
<namePart type="family">Caseli</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>Metaphor is a pervasive phenomenon in language that shapes how people conceptualize and communicate complex ideas. Detecting and interpreting metaphor is not only relevant for linguistic theory but also for many Natural Language Processing (NLP) applications, from machine translation to sentiment analysis, to mention a few. Despite its relevance, no open-source annotated corpus of metaphors exists for one of the world’s most widely spoken languages: Brazilian Portuguese. This paper addresses this gap by presenting an extension of Meta4XNLI, Meta4XNLI-ptBR, with token-level metaphor annotation in Brazilian Portuguese. To achieve this, we propose a pipeline that combines automatic translation via language models with human annotation, following guidelines adapted from MIPVU and Meta4XNLI. The final corpus contains 1,784 human-annotated sentences, of which 42.26% contain at least one metaphorical token. To our knowledge, this is the first open corpus of its kind for Brazilian Portuguese, and it is already freely available.</abstract>
<identifier type="citekey">johansson-etal-2026-meta4xnli</identifier>
<identifier type="doi">10.63317/45566xcgz65x</identifier>
<location>
<url>https://aclanthology.org/2026.lrec-1.131/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>1668</start>
<end>1676</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Meta4XNLI-ptBR: Brazilian Portuguese Extension of Meta4XNLI Corpus
%A Johansson, Karina
%A Assi, Fernanda
%A da Silva, Isabella
%A Passador, Rafael
%A Rodrigues, Isabela
%A Paes, Aline
%A Caseli, Helena
%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 johansson-etal-2026-meta4xnli
%X Metaphor is a pervasive phenomenon in language that shapes how people conceptualize and communicate complex ideas. Detecting and interpreting metaphor is not only relevant for linguistic theory but also for many Natural Language Processing (NLP) applications, from machine translation to sentiment analysis, to mention a few. Despite its relevance, no open-source annotated corpus of metaphors exists for one of the world’s most widely spoken languages: Brazilian Portuguese. This paper addresses this gap by presenting an extension of Meta4XNLI, Meta4XNLI-ptBR, with token-level metaphor annotation in Brazilian Portuguese. To achieve this, we propose a pipeline that combines automatic translation via language models with human annotation, following guidelines adapted from MIPVU and Meta4XNLI. The final corpus contains 1,784 human-annotated sentences, of which 42.26% contain at least one metaphorical token. To our knowledge, this is the first open corpus of its kind for Brazilian Portuguese, and it is already freely available.
%R 10.63317/45566xcgz65x
%U https://aclanthology.org/2026.lrec-1.131/
%U https://doi.org/10.63317/45566xcgz65x
%P 1668-1676
Markdown (Informal)
[Meta4XNLI-ptBR: Brazilian Portuguese Extension of Meta4XNLI Corpus](https://aclanthology.org/2026.lrec-1.131/) (Johansson et al., LREC 2026)
ACL
- Karina Johansson, Fernanda Assi, Isabella da Silva, Rafael Passador, Isabela Rodrigues, Aline Paes, and Helena Caseli. 2026. Meta4XNLI-ptBR: Brazilian Portuguese Extension of Meta4XNLI Corpus. In Proceedings of the Fifteenth Language Resources and Evaluation Conference, pages 1668–1676, Palma de Mallorca, Spain. ELRA Language Resource Association.