@inproceedings{guimaraes-etal-2026-developing,
title = "Developing Multilingual Multiword Expressions ({MWE}s) Resources: An Annotated Corpus of Fables following the {PARSEME} guidelines",
author = "Guimar{\~a}es, Let{\'i}cia Guedes and
Pagano, Adriana and
Coneglian, Andr{\'e} V. Lopes and
Villavicencio, Aline",
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-1.17/",
doi = "10.5753/stil.2026.26591",
pages = "200--208",
abstract = "This paper introduces a Brazilian Portuguese corpus of fables developed as part of a broader multilingual initiative. It comprises the narratives and their concluding moral statements (epimythia), annotated for morphosyntax and multiword expressions (MWEs) according to the Universal Dependencies (UD) and PARSEME guidelines, respectively. The analysis reveals that 53.59{\%} of the sentences contain at least one MWE, with inherently reflexive verbs (IRVs) constituting the most frequent category. MWEs are also distributed differently: narratives contain a higher proportion of adverbial MWEs, whereas adpositional MWEs are frequent in epimythia. Future work will enrich the corpus through semantic annotation based on Uniform Meaning Representation (UMR)."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="guimaraes-etal-2026-developing">
<titleInfo>
<title>Developing Multilingual Multiword Expressions (MWEs) Resources: An Annotated Corpus of Fables following the PARSEME guidelines</title>
</titleInfo>
<name type="personal">
<namePart type="given">Letícia</namePart>
<namePart type="given">Guedes</namePart>
<namePart type="family">Guimarães</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Adriana</namePart>
<namePart type="family">Pagano</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">André</namePart>
<namePart type="given">V</namePart>
<namePart type="given">Lopes</namePart>
<namePart type="family">Coneglian</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aline</namePart>
<namePart type="family">Villavicencio</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 introduces a Brazilian Portuguese corpus of fables developed as part of a broader multilingual initiative. It comprises the narratives and their concluding moral statements (epimythia), annotated for morphosyntax and multiword expressions (MWEs) according to the Universal Dependencies (UD) and PARSEME guidelines, respectively. The analysis reveals that 53.59% of the sentences contain at least one MWE, with inherently reflexive verbs (IRVs) constituting the most frequent category. MWEs are also distributed differently: narratives contain a higher proportion of adverbial MWEs, whereas adpositional MWEs are frequent in epimythia. Future work will enrich the corpus through semantic annotation based on Uniform Meaning Representation (UMR).</abstract>
<identifier type="citekey">guimaraes-etal-2026-developing</identifier>
<identifier type="doi">10.5753/stil.2026.26591</identifier>
<location>
<url>https://aclanthology.org/2026.stil-1.17/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>200</start>
<end>208</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Developing Multilingual Multiword Expressions (MWEs) Resources: An Annotated Corpus of Fables following the PARSEME guidelines
%A Guimarães, Letícia Guedes
%A Pagano, Adriana
%A Coneglian, André V. Lopes
%A Villavicencio, Aline
%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 guimaraes-etal-2026-developing
%X This paper introduces a Brazilian Portuguese corpus of fables developed as part of a broader multilingual initiative. It comprises the narratives and their concluding moral statements (epimythia), annotated for morphosyntax and multiword expressions (MWEs) according to the Universal Dependencies (UD) and PARSEME guidelines, respectively. The analysis reveals that 53.59% of the sentences contain at least one MWE, with inherently reflexive verbs (IRVs) constituting the most frequent category. MWEs are also distributed differently: narratives contain a higher proportion of adverbial MWEs, whereas adpositional MWEs are frequent in epimythia. Future work will enrich the corpus through semantic annotation based on Uniform Meaning Representation (UMR).
%R 10.5753/stil.2026.26591
%U https://aclanthology.org/2026.stil-1.17/
%U https://doi.org/10.5753/stil.2026.26591
%P 200-208
Markdown (Informal)
[Developing Multilingual Multiword Expressions (MWEs) Resources: An Annotated Corpus of Fables following the PARSEME guidelines](https://aclanthology.org/2026.stil-1.17/) (Guimarães et al., STIL 2026)
ACL