English

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

Computation and Language 2021-02-01 v2

Abstract

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.

Keywords

Cite

@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).

R2 v1 2026-06-23T21:53:26.097Z