SIGLEX-MWE Section - 22nd Workshop on Multiword Expressions (MWE 2026)

22^nd Workshop on Multiword Expressions (MWE 2026)

Colocated with: EACL-2026, Rabat, Marocco

Date of the Workshop: 28 March, 9:00-12:30

Organised and sponsored by:
The Special Interest Group on the Lexicon (SIGLEX) of the Association for Computational Linguistics (ACL), SIGLEX’s Multiword Expressions Section (SIGLEX-MWE), UniDive COST Action CA21167.

@multiword

News

Contents on this page

Proceedings and video recording
Program
Registration
Description
Shared tasks
Submission Formats
Paper Submission and Templates
In Memoriam
Important Dates
Organizing Committee
Program Committee
Sponsors and Support
Anti-harassment Policy
Contact

Proceedings and video recording

TBA

Program

Time	Session
09:00–09:15	Welcome and Introduction to 22nd MWE Workshop
09:15–09:45	Findings of the MWE 2026 Shared Tasks
	Edition 2.0 of the PARSEME shared task on multilingual identification and paraphrasing of multiword expressions Manon Scholivet, Agata Savary, Carlos Ramisch, Eric Bilinski, Takuya Nakamura, Maria Mitrofan and Vasile Pais
	MWE-2026 Shared Task: AdMIRe 2 Advancing Multimodal Idiomaticity Representation Doğukan Arslan, Rodrigo Wilkens, Wei He, Dilara Torunoglu Selamet, Thomas Pickard, Aline Villavicencio, Adriana Silvina Pagano and Gülşen Eryiğit
09:45–10:30	Poster session
	Large Language Models Put to the Test on Chinese Noun Compounds: Experiments on Natural Language Inference and Compound Semantics Le Qiu, Emmanuele Chersoni, He Zhou and Yu-Yin Hsu
	SinFoS: A Parallel Dataset for Translating Sinhala Figures of Speech Johan Nevin Sofalas, Dilushri Pavithra, Nevidu Jayatilleke and Ruvan Weerasinghe
	Ukrainian Multiword Expressions Corpus: Creation, Annotation, and Linguistic Analysis Hanna Sytar, Maria Shvedova and Olha Kanishcheva
	Cheese it up: CamemBERT Outperforms Large Language Models for Identification of French Multi-word Expressions Sergei Bagdasarov, Diego Alves and Elke Teich
	Extracting Multi-Word Expressions Representing Technical Terms and Proper Nouns in Log Messages Kilian Dangendorf, Sven-Ove Hänsel, Jannik Rosendahl, Felix Heine, Carsten Kleiner and Christian Wartena
	Two Birds with One Stone: Annotating Romanian Multiword Expressions with an Eye to the PARSEME 2.0 Guidelines Applicability Verginica Mititelu, Mihaela Cristescu, Elena Irimia and Carmen Mîrzea Vasile
	Incorporating Multiword Expressions in Galician Neural Machine Translation: Compositionality, Efficiency, and Performance Daniel Solla, Paula Pinto-Ferro, Laura Castro, Pablo Gamallo and Marcos Garcia
	Beyond Single Words: MWE Identification in Bioinformatics Research Articles and Dispersion Profiling Across IMRaD Jurgi Giraud and Andrew Gargett
	The Lock, Stock, and Barrel of Marathi Multiwords Aakanksha Padhye and Ashwini Vaidya
	An Idiom Benchmark for Turkish Ebru Çavuşoğlu and Cagri Coltekin
	A Curious Class of Adpositional Multiword Expressions in Korean Junghyun Min, Na-Rae Han, Jena D. Hwang and Nathan Schneider
	PolyFrame at MWE-2026 AdMIRe 2: When Words Are Not Enough: Multimodal Idiom Disambiguation Nina Hosseini-Kivanani
	IdiomRanker-X at MWE-2026 AdMIRe 2: Multilingual Idiom-Image Alignment via Low-Rank Adaptation of Cross-Encoders Mehmet Utku Colak
	alexandru412 at MWE-2026 AdMIRe 2.0: Advancing Multimodal Idiomaticity Representation Cristea Alexandru-Marian
	BeeParser at MWE-2026 PARSEME 2.0 Subtask 1: Can Cross-Lingual Interactions Improve MWE Identification? Ahmet Erdem and Oguzhan Karaarslan
	VisAffect at MWE-2026 AdMIRe 2: IMMCAN Idiom Multimodal Cross-Attention Network Barış Bilen, Ali Azmoudeh, Hazım Kemal Ekenel and Hatice Kose
	Sahara Tokenizers at PARSEME 2.0 Subtask 1: Combining Contextual Embeddings with Structural Decoding for Multi-Word Expression Detection Yunus Karatepe, Mert Sülük, Zeynep Tuğçe Kırımlı and Begüm Özbay
	3K2T at MWE-2026 AdMIRe 2: CARIM– Category-Aware Reasoning for Idiomatic Multimodality Kubilay Kağan Kömürcü and Tugce Temel
	PMI MWE Scorer at PARSEME 2.0 Subtask 1: identifying multi-word expressions using pointwise mutual information and universal dependencies Anna Bogdanova and Ileana Bucur
	tiberiucarp at MWE-2026 AdMIRe 2: GLIMMER-Gloss-based Image Multiword Meaning Expression Ranker Andrei Tiberiu Carp
	IPN at MWE-2026 PARSEME 2.0 Subtask 1: MWE Identification via Related Languages and Harnessing Thinking Mode Anna Hülsing, Noah-Manuel Michael, Daniel Mora Melanchthon and Andrea Horbach
	Semantic Stars at MWE-2026 PARSEME 2.0 Subtask 2: Alternative Approaches for MWE Paraphrasing Elif Bayraktar, Vedat Doğancan, Muhammed Abdullah Gümüş and Nusret Ali Kızılaslan
	MorphoFiltered-Gemini at MWE-2026 PARSEME 2.0 Subtask 1: Tackling LLM Overgeneration via Universal POS-based Constraints Irina Moise and Sergiu Nisioi
	LST at MWE-2026 AdMIRe 2: Advancing Multimodal Idiomaticity Representation Le Qiu, Yu-Yin Hsu and Emmanuele Chersoni
	UniBO at MWE-2026 PARSEME 2.0 Subtask 2: A Cross-lingual Approach to Multiword Expression Paraphrasing Debora Ciminari and Alberto Barrón-Cedeño
	DCSN-NLP at MWE-2026 AdMIRe 2: Bridging Literal and Figurative Meaning Through Hierarchical Multimodal Reasoning David Cotiga and Sergiu Nisioi
	ITUNLP at MWE-2026 AdMIRe 2: A Zero-Shot LLM Pipeline for Multimodal Idiom Understanding and Ranking Atakan Site, Oğuz Ali Arslan and Gülşen Eryiğit
	Archaeology at WE-2026 PARSEME 2.0 Subtask 1 and 2: Parsing is for Encoders, Paraphrasing is for LLMs Rares-Alexandru Roscan and Sergiu Nisioi
	ITUNLP2 at MWE-2026 AdMIRe 2: Modular Zero-Shot Pipelines for Multimodal Idiom Grounding and Ranking Özge Umut and Bora Şenceylan
10:30–11:00	Coffee break
11:00–11:45	Oral session
	Session chair: TBA
	Swedish Multiword Expression Corpora in PARSEME Sara Stymne, Astrid Berntsson Ingelstam and Eva Pettersson
	Cognitive Signatures of Multi-Word Expressions: Reading-Time and Surprisal Diego Alves, Sergei Bagdasarov and Elke Teich
	Diversity patterns run deep: Impact of diversity intake on multiword expression identification Mathilde Deletombe, Manon Scholivet, Louis Estève, Thomas Lavergne and Agata Savary
11:45–12:05	Community discussion
12:05–12:15	Concluding remarks

Registration

To attend the workshop (either in person or virtually), please register through EACL 2026’s registration system. Note that to attend MWE 2026, it is sufficient to select this workshop during registration; you do not have to register for the main conference.

Description

Multiword expressions (MWEs), i.e., word combinations that exhibit lexical, syntactic, semantic, pragmatic, and/or statistical idiosyncrasies (Baldwin and Kim, 2010), such as “by and large”, “hot dog”, “make a decision” and “break one’s leg” are still a pain in the neck for Natural Language Processing (NLP). The notion of MWE encompasses closely related phenomena: idioms, compounds, light-verb constructions, phrasal verbs, rhetorical figures, collocations, institutionalized phrases, etc. Given their irregular nature, MWEs often pose complex problems in linguistic modeling (e.g., annotation), NLP tasks (e.g., parsing), and end-user applications (e.g., natural language understanding and Machine Translation), hence still representing an open issue for computational linguistics (Miletić and Schulte im Walde, 2024; Ramisch et al., 2023; Phelps et al., 2024; Mahajan et al., 2024).

For more than two decades, the topic of modeling and processing MWEs for NLP has been the focus of the MWE workshop, organized by the MWE section of ACL-SIGLEX in conjunction with major NLP conferences since 2003. Impressive progress has been made in the field, but our understanding of MWEs still requires much research, considering their need and usefulness in NLP applications. This is also relevant to domain-specific NLP pipelines that need to tackle terminologies most often realized as MWEs.

Topics of interest include, but are not limited to:

Computationally-applicable theoretical work in psycholinguistics and corpus linguistics;
Annotation (expert, crowdsourcing, automatic) and representation in resources such as corpora, treebanks, e-lexicons, WordNets, constructions (also for low-resource languages);
Processing in syntactic and semantic frameworks (e.g. CCG, CxG, HPSG, LFG, TAG, UD, etc.);
Discovery and identification methods, including for specialized languages and domains such as clinical or biomedical NLP;
Interpretation of MWEs and understanding of text containing them;
Language acquisition, language learning, and non-standard language (e.g. tweets, speech);
Evaluation of annotation and processing techniques;
Retrospective comparative analyses from the PARSEME shared tasks;
Processing for end-user applications (e.g. MT, NLU, summarisation, language learning, etc.);
Implicit and explicit representation in pre-trained language models and end-user applications;
Evaluation and probing of pre-trained language models;
Resources and tools (e.g. lexicons, identifiers) and their integration into end-user applications;
Multiword terminology extraction;
Adaptation and transfer of annotations and related resources to new languages and domains including low-resource ones.

Co-located Shared tasks

The workshop MWE 2026 will host two shared tasks:

PARSEME 2.0, whose objective is to identify and paraphrase MWEs in written text, and
AdMIRe 2 (Advancing Multimodal Idiomaticity Representation), which explores the comprehension ability of multimodal models for MWEs in a variety of languages.

Submission Formats

The workshop invites two types of submissions: 

Archival submissions that present substantially original research in both long paper format (8 pages + references) and short paper format (4 pages + references)
Non-archival submissions of abstracts describing relevant research presented/published elsewhere which will not be included in the MWE proceedings (8 pages + references).

Paper Submission and Templates

Papers should be submitted via the workshop’s submission page. Please choose the appropriate submission format (archival/non-archival). Archival papers with existing reviews will also be accepted through the ACL Rolling Review. Submissions must follow the ACL stylesheet.

Authors are encouraged, wherever relevant, to adopt the conventions on citing, glossing and translating multilingual examples of MWEs promoted by the editors of the Phraseology and Multiword Expressions book series published by Language Science Press.

In Memoriam

The PARSEME community wishes to pay tribute to two of our colleagues who passed away in 2025: Federico Sangati and Silvio Ricardo Cordeiro, two wonderful people who greatly contributed to our assets.

Read the full tribute here

Important Dates

What	When
Direct Submission deadline	December 19 27, 2025
Pre-reviewed (ARR) submission deadline	January 5, 2026
Notification of acceptance	January 23 27, 2026
Camera-ready papers due	February 7, 2026
Workshop	March 28, 2026

All deadlines are at 23:59 UTC-12 (Anywhere on Earth).

Organizing Committee (Listed alphabetically)

Verginica Barbu Mititelu	Romanian Academy Research Institute for Artificial Intelligence
A. Seza Doğruöz	Ghent University, Belgium
Alexandre Rademaker	FGV/EMA, Brazil
Atul Kr. Ojha	Insight Research Ireland Centre for Data Analytics, University of Galway
Ivelina Stoyanova	Institute for Bulgarian Language
Mathieu Constant	Université de Lorraine

Program Committee

Abigail Walsh	Dublin City University
Agata Savary	Université Paris-Saclay
Ahmet Erdem	Istanbul Technical University
Alberto Barrón-Cedeño	Università di Bologna
Ali Azmoudeh	Istanbul Technical University
Andrea Horbach	Leibniz Institute for Science and Mathematics Education
Andrei Tiberiu Carp	Tomorrow University of Applied Sciences
Anna Hülsing	Christian-Albrechts-Universität Kiel
Atakan Site	Istanbul Technical University
Barış Bilen	Istanbul Technical University
Beata Trawinski	Leibniz Institute for the German Language
Bora Şenceylan	Istanbul Technical University
Carlos Ramisch	LIS - Laboratoire d’Informatique et Systèmes
Chikara Hashimoto	Rakuten Institute of Technology
Cristea Alexandru-Marian	University of Bucharest
Cvetana Krstev	University of Belgrade, Faculty of Philology
David Cotigă	University of Bucharest
Debora Ciminari	University of Bologna
Doğukan Arslan	Istanbul Technical University
Elif Bayraktar	Istanbul Technical University
Emmanuele Chersoni	The Hong Kong Polytechnic University
Eric G C Laporte	Université Gustave Eiffel
Gaël Dias	University of Caen Normandy
Gražina Korvel	Vilnius University
Gülşen Eryiğit	Istanbul Technical University
Irina Lobzhanidze	Ilia Chavchavadze State University
Irina Moise	University of Bucharest
Ismail El Maarouf	Imprevicible
Ivelina Stoyanova	Deaf Studies Institute
Jan Odijk	Utrecht University
John Philip McCrae	University of Galway
Kenneth Church	Northeastern University
Kubilay Kağan Kömürcü	Istanbul Technical University
Laura A. Michaelis	University of Colorado at Boulder
Le Qiu	The Hong Kong Polytechnic University
Manfred Sailer	Johann Wolfgang Goethe Universität Frankfurt am Main
Manon Scholivet	Université Paris-Saclay
Maria Mitrofan	Research Institute for Artificial Intelligence
Mathieu Constant	Université de Lorraine, CNRS, ATILF
Matthew Shardlow	The Manchester Metropolitan University
Meghdad Farahmand	University of Genoa
Mehmet Utku Colak	Istanbul Technical University
Miriam Butt	Universität Konstanz
Monika Czerepowicka	University of Wamia and Masuria
Muhammed Abdullah Gümüş	International Technological University
Nina Hosseini-Kivanani	RTL
Oğuz Ali Arslan	Istanbul Technical University
Özge Umut	Istanbul Technical University
Oguzhan Karaarslan	Istanbul Technical University
Paul Cook	University of New Brunswick
Petya Osenova	Sofia University St. Kliment Ohridski
Ranka Stanković Stanković	University of Belgrade
Rares-Alexandru Roscan	University of Bucharest
Sabine Schulte im Walde	University of Stuttgart
Sergiu Nisioi	University of Bucharest
Shiva Taslimipoor	University of Cambridge
Stan Szpakowicz	University of Ottawa
Stella Markantonatou	ATHENA RIC
Tugce Temel	Istanbul Technical University
Tiberiu Boros	Adobe Systems
Tunga Gungor	Bogazici University
Veronika Vincze	University of Szeged
Yu-Yin Hsu	The Hong Kong Polytechnic University
Yunus Karatepe	International Technological University