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

Code

• github.com/osainz59/Ask2Transformers
  OfficialIn paperpytorch★ 152

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.

Tasks

Benchmark Results

Reproductions