@inproceedings{sentsova-etal-2025-multicopie,
title = "{M}ulti{C}o{PIE}: A Multilingual Corpus of Potentially Idiomatic Expressions for Cross-lingual {PIE} Disambiguation",
author = "Sentsova, Uliana and
Ciminari, Debora and
Genabith, Josef Van and
Espa{\~n}a-Bonet, Cristina",
editor = {Ojha, Atul Kr. and
Giouli, Voula and
Mititelu, Verginica Barbu and
Constant, Mathieu and
Korvel, Gra{\v{z}}ina and
Do{\u{g}}ru{\"o}z, A. Seza and
Rademaker, Alexandre},
booktitle = "Proceedings of the 21st Workshop on Multiword Expressions (MWE 2025)",
month = may,
year = "2025",
address = "Albuquerque, New Mexico, U.S.A.",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.mwe-1.8/",
doi = "10.18653/v1/2025.mwe-1.8",
pages = "67--81",
ISBN = "979-8-89176-243-5",
abstract = "Language models are able to handle compositionality and, to some extent, non-compositional phenomena such as semantic idiosyncrasy, a feature most prominent in the case of idioms. This work introduces the MultiCoPIE corpus that includes potentially idiomatic expressions in Catalan, Italian, and Russian, extending the language coverage of PIE corpus data. The new corpus provides additional linguistic features of idioms, such as their semantic compositionality, part-of-speech of idiom head as well as their corresponding idiomatic expressions in English. With this new resource at hand, we first fine-tune an XLM-RoBERTa model to classify figurative and literal usage of potentially idiomatic expressions in English. We then study cross-lingual transfer to the languages represented in the MultiCoPIE corpus, evaluating the model{'}s ability to generalize an idiom-related task to languages not seen during fine-tuning. We show the effect of `cross-lingual lexical overlap': the performance of the model, fine-tuned on English idiomatic expressions and tested on the MultiCoPIE languages, increases significantly when classifying `shared idioms' -idiomatic expressions that have direct counterparts in English with similar form and meaning. While this observation raises questions about the generalizability of cross-lingual learning, the results from experiments on PIEs demonstrate strong evidence of effective cross-lingual transfer, even when accounting for idioms similar across languages."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sentsova-etal-2025-multicopie">
<titleInfo>
<title>MultiCoPIE: A Multilingual Corpus of Potentially Idiomatic Expressions for Cross-lingual PIE Disambiguation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Uliana</namePart>
<namePart type="family">Sentsova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Debora</namePart>
<namePart type="family">Ciminari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Josef</namePart>
<namePart type="given">Van</namePart>
<namePart type="family">Genabith</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Cristina</namePart>
<namePart type="family">España-Bonet</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 21st Workshop on Multiword Expressions (MWE 2025)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Atul</namePart>
<namePart type="given">Kr.</namePart>
<namePart type="family">Ojha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Voula</namePart>
<namePart type="family">Giouli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Verginica</namePart>
<namePart type="given">Barbu</namePart>
<namePart type="family">Mititelu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mathieu</namePart>
<namePart type="family">Constant</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gražina</namePart>
<namePart type="family">Korvel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">A</namePart>
<namePart type="given">Seza</namePart>
<namePart type="family">Doğruöz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alexandre</namePart>
<namePart type="family">Rademaker</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Albuquerque, New Mexico, U.S.A.</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-243-5</identifier>
</relatedItem>
<abstract>Language models are able to handle compositionality and, to some extent, non-compositional phenomena such as semantic idiosyncrasy, a feature most prominent in the case of idioms. This work introduces the MultiCoPIE corpus that includes potentially idiomatic expressions in Catalan, Italian, and Russian, extending the language coverage of PIE corpus data. The new corpus provides additional linguistic features of idioms, such as their semantic compositionality, part-of-speech of idiom head as well as their corresponding idiomatic expressions in English. With this new resource at hand, we first fine-tune an XLM-RoBERTa model to classify figurative and literal usage of potentially idiomatic expressions in English. We then study cross-lingual transfer to the languages represented in the MultiCoPIE corpus, evaluating the model’s ability to generalize an idiom-related task to languages not seen during fine-tuning. We show the effect of ‘cross-lingual lexical overlap’: the performance of the model, fine-tuned on English idiomatic expressions and tested on the MultiCoPIE languages, increases significantly when classifying ‘shared idioms’ -idiomatic expressions that have direct counterparts in English with similar form and meaning. While this observation raises questions about the generalizability of cross-lingual learning, the results from experiments on PIEs demonstrate strong evidence of effective cross-lingual transfer, even when accounting for idioms similar across languages.</abstract>
<identifier type="citekey">sentsova-etal-2025-multicopie</identifier>
<identifier type="doi">10.18653/v1/2025.mwe-1.8</identifier>
<location>
<url>https://aclanthology.org/2025.mwe-1.8/</url>
</location>
<part>
<date>2025-05</date>
<extent unit="page">
<start>67</start>
<end>81</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T MultiCoPIE: A Multilingual Corpus of Potentially Idiomatic Expressions for Cross-lingual PIE Disambiguation
%A Sentsova, Uliana
%A Ciminari, Debora
%A Genabith, Josef Van
%A España-Bonet, Cristina
%Y Ojha, Atul Kr.
%Y Giouli, Voula
%Y Mititelu, Verginica Barbu
%Y Constant, Mathieu
%Y Korvel, Gražina
%Y Doğruöz, A. Seza
%Y Rademaker, Alexandre
%S Proceedings of the 21st Workshop on Multiword Expressions (MWE 2025)
%D 2025
%8 May
%I Association for Computational Linguistics
%C Albuquerque, New Mexico, U.S.A.
%@ 979-8-89176-243-5
%F sentsova-etal-2025-multicopie
%X Language models are able to handle compositionality and, to some extent, non-compositional phenomena such as semantic idiosyncrasy, a feature most prominent in the case of idioms. This work introduces the MultiCoPIE corpus that includes potentially idiomatic expressions in Catalan, Italian, and Russian, extending the language coverage of PIE corpus data. The new corpus provides additional linguistic features of idioms, such as their semantic compositionality, part-of-speech of idiom head as well as their corresponding idiomatic expressions in English. With this new resource at hand, we first fine-tune an XLM-RoBERTa model to classify figurative and literal usage of potentially idiomatic expressions in English. We then study cross-lingual transfer to the languages represented in the MultiCoPIE corpus, evaluating the model’s ability to generalize an idiom-related task to languages not seen during fine-tuning. We show the effect of ‘cross-lingual lexical overlap’: the performance of the model, fine-tuned on English idiomatic expressions and tested on the MultiCoPIE languages, increases significantly when classifying ‘shared idioms’ -idiomatic expressions that have direct counterparts in English with similar form and meaning. While this observation raises questions about the generalizability of cross-lingual learning, the results from experiments on PIEs demonstrate strong evidence of effective cross-lingual transfer, even when accounting for idioms similar across languages.
%R 10.18653/v1/2025.mwe-1.8
%U https://aclanthology.org/2025.mwe-1.8/
%U https://doi.org/10.18653/v1/2025.mwe-1.8
%P 67-81
Markdown (Informal)
[MultiCoPIE: A Multilingual Corpus of Potentially Idiomatic Expressions for Cross-lingual PIE Disambiguation](https://aclanthology.org/2025.mwe-1.8/) (Sentsova et al., MWE 2025)
ACL