Papers with transferable components
A Two Stage Adaptation Framework for Frame Detection via Prompt Learning (2022.coling-1)
Copied to clipboard
| Challenge: | Existing frameworks focus on a single scenario or issue, ignoring the special characteristics of frame detection that new events emerge continuously and policy agenda changes dynamically. |
| Approach: | They propose a framework to adapt to different contexts and frame typologies . they propose coding tasks that learn transferable encoders and verbalizers based on pivots and prompts - and generalization tasks that apply them to new issues and label sets. |
| Outcome: | The proposed framework shows superiority in both full-resource and low-resourced conditions. |