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.
@article{arxiv.2101.02661,
title = {Ask2Transformers: Zero-Shot Domain labelling with Pre-trained Language Models},
author = {Oscar Sainz and German Rigau},
journal= {arXiv preprint arXiv:2101.02661},
year = {2021}
}
Comments
Accepted on Proceedings of the 11th Global WordNet Conference (GWC 2021).