Ask2Transformers: Zero-Shot Domain labelling with Pre-trained Language Models

01/07/2021

∙

by   Oscar Sainz, et al.

∙

0

∙

share

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.