Funzac at CoMeDi Shared Task: Modeling Annotator Disagreement from Word-In-Context Perspectives

Olufunke O. Sarumi, Charles Welch, Lucie Flek, Jörg Schlötterer


Abstract
In this work, we evaluate annotator disagreement in Word-in-Context (WiC) tasks exploring the relationship between contextual meaning and disagreement as part of the CoMeDi shared task competition. While prior studies have modeled disagreement by analyzing annotator attributes with single-sentence inputs, this shared task incorporates WiC to bridge the gap between sentence-level semantic representation and annotator judgment variability. We describe three different methods that we developed for the shared task, including a feature enrichment approach that combines concatenation, element-wise differences, products, and cosine similarity, Euclidean and Manhattan distances to extend contextual embedding representations, a transformation by Adapter blocks to obtain task-specific representations of contextual embeddings, and classifiers of varying complexities, including ensembles. The comparison of our methods demonstrates improved performance for methods that include enriched and task-specfic features. While the performance of our method falls short in comparison to the best system in subtask 1 (OGWiC), it is competitive to the official evaluation results in subtask 2 (DisWiC)
Anthology ID:
2025.comedi-1.8
Volume:
Proceedings of Context and Meaning: Navigating Disagreements in NLP Annotation
Month:
January
Year:
2025
Address:
Abu Dhabi, UAE
Editors:
Michael Roth, Dominik Schlechtweg
Venues:
CoMeDi | WS
SIG:
Publisher:
International Committee on Computational Linguistics
Note:
Pages:
90–96
Language:
URL:
https://aclanthology.org/2025.comedi-1.8/
DOI:
Bibkey:
Cite (ACL):
Olufunke O. Sarumi, Charles Welch, Lucie Flek, and Jörg Schlötterer. 2025. Funzac at CoMeDi Shared Task: Modeling Annotator Disagreement from Word-In-Context Perspectives. In Proceedings of Context and Meaning: Navigating Disagreements in NLP Annotation, pages 90–96, Abu Dhabi, UAE. International Committee on Computational Linguistics.
Cite (Informal):
Funzac at CoMeDi Shared Task: Modeling Annotator Disagreement from Word-In-Context Perspectives (Sarumi et al., CoMeDi 2025)
Copy Citation:
PDF:
https://aclanthology.org/2025.comedi-1.8.pdf