The 23rd Workshop on Multiword Expressions (MWE 2027) 🔗 https://multiword.org/mwe2027/ 📍Athens, Greece 𝕏 https://x.com/mweworkshop 🦋 https://bsky.app/profile/mwe-workshop.bsky.social
Full day workshop colocated with the 20th Conference of the European Chapter of the Association for Computational Linguistics ( EACL 2027 , [ https://2027.eacl.org/ | https://2027.eacl.org/ ] ) Organised, sponsored, and endorsed by SIGLEX , the Special Interest Group on the Lexicon of the ACL.
--------------------------------------------------------------------------------------
Important Dates
Direct Submission deadline: December 1, 2026 Pre-reviewed (ARR) submission deadline: December 22, 2026 Notification of acceptance: TBA (January 2027) Camera-ready paper due: January 19, 2027 Workshop date: one full day between March 9–14, 2027 (exact date TBA)
All deadlines are at 23:59 UTC-12 (Anywhere on Earth).
--------------------------------------------------------------------------------------
Overview
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. The notion of MWE encompasses closely related phenomena: idioms, compounds, light-verb constructions, phrasal verbs, rhetorical figures, collocations, institutionalised phrases, etc. Given their irregular nature, MWEs often pose complex problems in linguistic modelling (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 modelling 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 substantial further research, given their importance and usefulness in NLP applications. This is also relevant to domain-specific NLP pipelines that need to tackle terminologies most often realised as MWEs.
Topics of interest include, but are not limited to:
* Linguistic aspects of MWE: criteria for their classification, morpho-syntactic and semantic idiosyncrasies, contrastive studies of MWEs in various languages; * MWE resources: corpora, dictionaries, lexicons, treebanks, mono-/multilingual, new and enhanced representation of MWEs in language resources, computational models of compositionality as gold standards for formative intrinsic evaluation, development of multilingual benchmarks for MWE identification; * MWE processing, identification, and recognition in the general language, as well as in specialised languages and domains, including in low-resourced languages; * MWEs in LLMs and embeddings: representation, compositionality, and phrase-level embeddings, adapting LLMs to better handle MWEs, probing LLMs’ understanding of MWEs; * MWE processing to enhance end-user applications.
--------------------------------------------------------------------------------------
Submission formats
The workshop invites three types of submissions:
* Archival submission of research papers that present substantially original research in both long paper format (8 pages + references) and short paper format (4 pages + references). * System and resource demonstrations that present tools and datasets related to MWEs and MWE processing , which could be demoed during the workshop. System/resource description papers should be up to 4 pages + references, and do not need to be anonymised. * Non-archival submissions describing relevant research presented/published elsewhere ; non-archival submissions will not be included in the MWE proceedings and do not need to be anonymised (they will not undergo reviews); they should contain a short abstract of the paper (1-2 pages) with a link to the already published paper.
--------------------------------------------------------------------------------------
Paper submission and templates
Papers should be submitted via the workshop's submission page (to be announced). Please choose the appropriate submission format (archival/system/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.
--------------------------------------------------------------------------------------
Organizing Committee
Patricia Chiril , Jaka ÄŚibej , Adriana Silvana Pagano , Ivelina Stoyanova , and Sara Stymne
Anti-harassment policy
The workshop follows the ACL anti-harassment policy.
Contact
For any inquiries regarding the workshop, please send an email to the Organizing Committee at siglex-mwe-board@googlegroups.com