@inproceedings{kalinina-etal-2026-learner,
title = "A Learner-Oriented Annotated Resource of {F}rench Multiword Expressions for Text Adaptation in Foreign Language Reading",
author = "Kalinina, Anna and
Fran{\c{c}}ois, Thomas and
Vassiliadou, H{\'e}l{\`e}ne and
Todirascu, Amalia",
editor = "Shardlow, Matthew and
Fran{\c{c}}ois, Thomas and
Amaro, Raquel and
Baptista, Jorge and
Cardon, R{\'e}mi and
Ribeiro, Eug{\'e}nio and
Saggion, Horacio and
Stodden, Regina and
Todirascu, Amalia and
Wilkens, Rodrigo",
booktitle = "Proceedings of the Joint Workshop on Readability and Text Simplification ({READI}x{TSAR}) @ {LREC} 2026",
month = may,
year = "2026",
address = "Palma, Mallorca (Spain)",
publisher = "ELRA Language Resources Association (ELRA)",
url = "https://aclanthology.org/2026.readi-1.14/",
doi = "10.63317/47m6wxhoqpej",
pages = "181--192",
abstract = "This article presents a learner-oriented annotated lexical resource of French multiword expressions (MWEs) designed to support text adaptation in foreign language reading. MWEs, including idioms and collocations, pose major comprehension challenges for learners because their meaning often cannot be inferred compositionally or depends on conventional lexical constraints. To address this issue, the study extends the existing verbal MWE database by integrating nominal and verbal MWEs annotated according to a linguistically grounded typology distinguishing idioms, opaque collocations, and transparent collocations. The resource was developed through a multi-step methodology combining automatic extraction from pedagogical corpora, manual annotation using decision-tree-based guidelines, and CEFR level assignment based on corpus distribution. The resulting dataset includes approximately 2,700 expressions enriched with detailed linguistic and learner-relevant metadata. Annotation campaigns involving native and non-native annotators showed moderate agreement, reflecting the gradient nature of phraseological opacity. By linking phraseological complexity with learner proficiency, this resource provides a reproducible framework for modeling MWE difficulty. It offers valuable support for text adaptation, readability assessment, and the development of NLP-based educational tools, contributing to improved accessibility of French texts for language learners."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kalinina-etal-2026-learner">
<titleInfo>
<title>A Learner-Oriented Annotated Resource of French Multiword Expressions for Text Adaptation in Foreign Language Reading</title>
</titleInfo>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Kalinina</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thomas</namePart>
<namePart type="family">François</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hélène</namePart>
<namePart type="family">Vassiliadou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Amalia</namePart>
<namePart type="family">Todirascu</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 Joint Workshop on Readability and Text Simplification (READIxTSAR) @ LREC 2026</title>
</titleInfo>
<name type="personal">
<namePart type="given">Matthew</namePart>
<namePart type="family">Shardlow</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thomas</namePart>
<namePart type="family">François</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Raquel</namePart>
<namePart type="family">Amaro</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jorge</namePart>
<namePart type="family">Baptista</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rémi</namePart>
<namePart type="family">Cardon</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eugénio</namePart>
<namePart type="family">Ribeiro</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Horacio</namePart>
<namePart type="family">Saggion</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Regina</namePart>
<namePart type="family">Stodden</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Amalia</namePart>
<namePart type="family">Todirascu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rodrigo</namePart>
<namePart type="family">Wilkens</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA Language Resources Association (ELRA)</publisher>
<place>
<placeTerm type="text">Palma, Mallorca (Spain)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This article presents a learner-oriented annotated lexical resource of French multiword expressions (MWEs) designed to support text adaptation in foreign language reading. MWEs, including idioms and collocations, pose major comprehension challenges for learners because their meaning often cannot be inferred compositionally or depends on conventional lexical constraints. To address this issue, the study extends the existing verbal MWE database by integrating nominal and verbal MWEs annotated according to a linguistically grounded typology distinguishing idioms, opaque collocations, and transparent collocations. The resource was developed through a multi-step methodology combining automatic extraction from pedagogical corpora, manual annotation using decision-tree-based guidelines, and CEFR level assignment based on corpus distribution. The resulting dataset includes approximately 2,700 expressions enriched with detailed linguistic and learner-relevant metadata. Annotation campaigns involving native and non-native annotators showed moderate agreement, reflecting the gradient nature of phraseological opacity. By linking phraseological complexity with learner proficiency, this resource provides a reproducible framework for modeling MWE difficulty. It offers valuable support for text adaptation, readability assessment, and the development of NLP-based educational tools, contributing to improved accessibility of French texts for language learners.</abstract>
<identifier type="citekey">kalinina-etal-2026-learner</identifier>
<identifier type="doi">10.63317/47m6wxhoqpej</identifier>
<location>
<url>https://aclanthology.org/2026.readi-1.14/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>181</start>
<end>192</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Learner-Oriented Annotated Resource of French Multiword Expressions for Text Adaptation in Foreign Language Reading
%A Kalinina, Anna
%A François, Thomas
%A Vassiliadou, Hélène
%A Todirascu, Amalia
%Y Shardlow, Matthew
%Y François, Thomas
%Y Amaro, Raquel
%Y Baptista, Jorge
%Y Cardon, Rémi
%Y Ribeiro, Eugénio
%Y Saggion, Horacio
%Y Stodden, Regina
%Y Todirascu, Amalia
%Y Wilkens, Rodrigo
%S Proceedings of the Joint Workshop on Readability and Text Simplification (READIxTSAR) @ LREC 2026
%D 2026
%8 May
%I ELRA Language Resources Association (ELRA)
%C Palma, Mallorca (Spain)
%F kalinina-etal-2026-learner
%X This article presents a learner-oriented annotated lexical resource of French multiword expressions (MWEs) designed to support text adaptation in foreign language reading. MWEs, including idioms and collocations, pose major comprehension challenges for learners because their meaning often cannot be inferred compositionally or depends on conventional lexical constraints. To address this issue, the study extends the existing verbal MWE database by integrating nominal and verbal MWEs annotated according to a linguistically grounded typology distinguishing idioms, opaque collocations, and transparent collocations. The resource was developed through a multi-step methodology combining automatic extraction from pedagogical corpora, manual annotation using decision-tree-based guidelines, and CEFR level assignment based on corpus distribution. The resulting dataset includes approximately 2,700 expressions enriched with detailed linguistic and learner-relevant metadata. Annotation campaigns involving native and non-native annotators showed moderate agreement, reflecting the gradient nature of phraseological opacity. By linking phraseological complexity with learner proficiency, this resource provides a reproducible framework for modeling MWE difficulty. It offers valuable support for text adaptation, readability assessment, and the development of NLP-based educational tools, contributing to improved accessibility of French texts for language learners.
%R 10.63317/47m6wxhoqpej
%U https://aclanthology.org/2026.readi-1.14/
%U https://doi.org/10.63317/47m6wxhoqpej
%P 181-192
Markdown (Informal)
[A Learner-Oriented Annotated Resource of French Multiword Expressions for Text Adaptation in Foreign Language Reading](https://aclanthology.org/2026.readi-1.14/) (Kalinina et al., READI-TSAR 2026)
ACL