Papers by Devansh Jain
Distilling Hypernymy Relations from Language Models: On the Effectiveness of Zero-Shot Taxonomy Induction (2022.starsem-1)
Copied to clipboard
| Challenge: | Earlier approaches to taxonomy learning focused on mining lexico-syntactic patterns from candidate pairs. |
| Approach: | They propose to use prompts to distill knowledge from language models to refine methods . they also show that linguistic properties of prompts dictate downstream performance . |
| Outcome: | The proposed methods outperform some supervised strategies and are competitive with the current state-of-the-art under adequate conditions. |