Ask2Transformers: Zero-Shot Domain labelling with Pre-trained Language Models
This work addresses the problem of automatically assigning domain labels to WordNet synsets for researchers and applications requiring semantic knowledge organization, offering an incremental improvement in performance.
This paper introduces a zero-shot system that leverages pre-trained Language Models to assign domain labels to WordNet synsets without supervision. The system achieves a new state-of-the-art on the English dataset used for evaluation.
In this paper we present a system that exploits different pre-trained Language Models for assigning domain labels to WordNet synsets without any kind of supervision. Furthermore, the system is not restricted to use a particular set of domain labels. We exploit the knowledge encoded within different off-the-shelf pre-trained Language Models and task formulations to infer the domain label of a particular WordNet definition. The proposed zero-shot system achieves a new state-of-the-art on the English dataset used in the evaluation.