@inproceedings{tedeschi-etal-2022-id10m,
title = "{ID}10{M}: Idiom Identification in 10 Languages",
author = "Tedeschi, Simone and
Martelli, Federico and
Navigli, Roberto",
editor = "Carpuat, Marine and
de Marneffe, Marie-Catherine and
Meza Ruiz, Ivan Vladimir",
booktitle = "Findings of the Association for Computational Linguistics: NAACL 2022",
month = jul,
year = "2022",
address = "Seattle, United States",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.findings-naacl.208",
doi = "10.18653/v1/2022.findings-naacl.208",
pages = "2715--2726",
abstract = "Idioms are phrases which present a figurative meaning that cannot be (completely) derived by looking at the meaning of their individual components. Identifying and understanding idioms in context is a crucial goal and a key challenge in a wide range of Natural Language Understanding tasks. Although efforts have been undertaken in this direction, the automatic identification and understanding of idioms is still a largely under-investigated area, especially when operating in a multilingual scenario. In this paper, we address such limitations and put forward several new contributions: we propose a novel multilingual Transformer-based system for the identification of idioms; we produce a high-quality automatically-created training dataset in 10 languages, along with a novel manually-curated evaluation benchmark; finally, we carry out a thorough performance analysis and release our evaluation suite at \url{https://github.com/Babelscape/ID10M}.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="tedeschi-etal-2022-id10m">
<titleInfo>
<title>ID10M: Idiom Identification in 10 Languages</title>
</titleInfo>
<name type="personal">
<namePart type="given">Simone</namePart>
<namePart type="family">Tedeschi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Federico</namePart>
<namePart type="family">Martelli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Roberto</namePart>
<namePart type="family">Navigli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: NAACL 2022</title>
</titleInfo>
<name type="personal">
<namePart type="given">Marine</namePart>
<namePart type="family">Carpuat</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marie-Catherine</namePart>
<namePart type="family">de Marneffe</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ivan</namePart>
<namePart type="given">Vladimir</namePart>
<namePart type="family">Meza Ruiz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Seattle, United States</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Idioms are phrases which present a figurative meaning that cannot be (completely) derived by looking at the meaning of their individual components. Identifying and understanding idioms in context is a crucial goal and a key challenge in a wide range of Natural Language Understanding tasks. Although efforts have been undertaken in this direction, the automatic identification and understanding of idioms is still a largely under-investigated area, especially when operating in a multilingual scenario. In this paper, we address such limitations and put forward several new contributions: we propose a novel multilingual Transformer-based system for the identification of idioms; we produce a high-quality automatically-created training dataset in 10 languages, along with a novel manually-curated evaluation benchmark; finally, we carry out a thorough performance analysis and release our evaluation suite at https://github.com/Babelscape/ID10M.</abstract>
<identifier type="citekey">tedeschi-etal-2022-id10m</identifier>
<identifier type="doi">10.18653/v1/2022.findings-naacl.208</identifier>
<location>
<url>https://aclanthology.org/2022.findings-naacl.208</url>
</location>
<part>
<date>2022-07</date>
<extent unit="page">
<start>2715</start>
<end>2726</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T ID10M: Idiom Identification in 10 Languages
%A Tedeschi, Simone
%A Martelli, Federico
%A Navigli, Roberto
%Y Carpuat, Marine
%Y de Marneffe, Marie-Catherine
%Y Meza Ruiz, Ivan Vladimir
%S Findings of the Association for Computational Linguistics: NAACL 2022
%D 2022
%8 July
%I Association for Computational Linguistics
%C Seattle, United States
%F tedeschi-etal-2022-id10m
%X Idioms are phrases which present a figurative meaning that cannot be (completely) derived by looking at the meaning of their individual components. Identifying and understanding idioms in context is a crucial goal and a key challenge in a wide range of Natural Language Understanding tasks. Although efforts have been undertaken in this direction, the automatic identification and understanding of idioms is still a largely under-investigated area, especially when operating in a multilingual scenario. In this paper, we address such limitations and put forward several new contributions: we propose a novel multilingual Transformer-based system for the identification of idioms; we produce a high-quality automatically-created training dataset in 10 languages, along with a novel manually-curated evaluation benchmark; finally, we carry out a thorough performance analysis and release our evaluation suite at https://github.com/Babelscape/ID10M.
%R 10.18653/v1/2022.findings-naacl.208
%U https://aclanthology.org/2022.findings-naacl.208
%U https://doi.org/10.18653/v1/2022.findings-naacl.208
%P 2715-2726
Markdown (Informal)
[ID10M: Idiom Identification in 10 Languages](https://aclanthology.org/2022.findings-naacl.208) (Tedeschi et al., Findings 2022)
ACL
- Simone Tedeschi, Federico Martelli, and Roberto Navigli. 2022. ID10M: Idiom Identification in 10 Languages. In Findings of the Association for Computational Linguistics: NAACL 2022, pages 2715–2726, Seattle, United States. Association for Computational Linguistics.