Distilling Hypernymy Relations from Language Models: On the Effectiveness of Zero-Shot Taxonomy Induction

Devansh Jain, Luis Espinosa-Anke

TL;DR: Evaluating pretrained language models for zero-shot taxonomy induction using prompting and sentence-scoring techniques.

Abstract: In this paper, we analyze zero-shot taxonomy learning methods which are based on distilling knowledge from language models via prompting and sentence scoring. We show that, despite their simplicity, these methods outperform some supervised strategies and are competitive with the current state-of-the-art under adequate conditions. We also show that statistical and linguistic properties of prompts dictate downstream performance.

Track: Non-Archival (will not appear in proceedings)

Acl Rolling Review: https://openreview.net/forum?id=Cwgk02w3N-6

Community Implementations: [ 1 code implementation](https://www.catalyzex.com/paper/distilling-hypernymy-relations-from-language/code)