Representing Multimodality in Terminology Resources
Proceedings of the Fifteenth Language Resources and Evaluation Conference (LREC 2026)
Abstract
This paper addresses the lack of a multimodal approach to specialized knowledge representation in terminology work. In particular, we introduce a new Multimodal Terminological Metamodel (MTM) for the design of terminology resources which introduces an explicit modality layer, enabling uniform modelling of different language modalities within domain-specific and concept-oriented resources. The metamodel is formalised via an entity-relationship schema and a systematic contrast with the baseline framework – the Terminological Markup Framework (TMF; ISO-16642 (2017)) – to specify revised entities, relations, and cardinalities. As case study, we instantiate the MTM for the signed modality by defining a minimal data-category module with level-placement constraints, and we provide a lightweight, TBX-inspired XML serialisation that packages modality-specific terminological data in a consistent structure. Together, these components deliver a reproducible specification for designing and exchanging multimodal terminology resources.