We are pleased to announce the SemEval-2027 Task on *Noun Compound and Particle Verb Compositionality Prediction in Context* (ComPartMent).
We introduce a shared task on in-context compositionality prediction: given a target multiword expression (a noun compound such as glass ceiling or a particle verb such as take off) and a sentence in which that expression is used, systems are expected to output numerical scores reflecting human ordinal compositionality ratings for the target expression in that context.
Our task addresses the compositionality prediction problem from several novel angles. We incorporate two types of multiword expressions (noun compounds and particle verbs) in two languages (English and German). For each of the 1,539 target expressions, we draw on two types of corpora (present-day and historical data) to provide ≈10 example sentences, each labeled with human ordinal compositionality ratings.
*Example ratings * (Scale: 0/clearly non-compositional - 5/clearly compositional)
*Noun compound examples (compound-modifier / compound-head ratings) *she propelled herself into the firing line in taking the stance she did (0.6 / 0.7) our flea market will feature some of the most creative individuals (0.0 / 4.7)
*Particle verb examples (overall rating)* it’s gonna get very cold so pull up your leggings (4.8) I will probably wind up as a Web Haunter […] blogging for eternity (0.2)
How to participate
*Task website*: https://sites.google.com/view/semeval-compartment *Task data, registration, and submissions*: CodaBench https://www.codabench.org/competitions/17971/
Important dates
September 5, 2026: Trial data release September 8, 2026: Training data release January 10, 2027: Evaluation start January 31, 2027: Evaluation end
Organizers
Filip Miletić, Chris Jenkins, Sabine Schulte im Walde Institute for Natural Language Processing (IMS), University of Stuttgart
Contact: semeval-compartment (at) ims (dot) uni-stuttgart (dot) de