A Two Stage Adaptation Framework for Frame Detection via Prompt Learning

Xinyi Mou, Zhongyu Wei, Changjian Jiang, Jiajie Peng


Abstract
Framing is a communication strategy to bias discussion by selecting and emphasizing. Frame detection aims to automatically analyze framing strategy. Previous works on frame detection mainly focus on a single scenario or issue, ignoring the special characteristics of frame detection that new events emerge continuously and policy agenda changes dynamically. To better deal with various context and frame typologies across different issues, we propose a two-stage adaptation framework. In the framing domain adaptation from pre-training stage, we design two tasks based on pivots and prompts to learn a transferable encoder, verbalizer, and prompts. In the downstream scenario generalization stage, the transferable components are applied to new issues and label sets. Experiment results demonstrate the effectiveness of our framework in different scenarios. Also, it shows superiority both in full-resource and low-resource conditions.
Anthology ID:
2022.coling-1.263
Volume:
Proceedings of the 29th International Conference on Computational Linguistics
Month:
October
Year:
2022
Address:
Gyeongju, Republic of Korea
Venue:
COLING
SIG:
Publisher:
International Committee on Computational Linguistics
Note:
Pages:
2968–2978
Language:
URL:
https://aclanthology.org/2022.coling-1.263
DOI:
Bibkey:
Cite (ACL):
Xinyi Mou, Zhongyu Wei, Changjian Jiang, and Jiajie Peng. 2022. A Two Stage Adaptation Framework for Frame Detection via Prompt Learning. In Proceedings of the 29th International Conference on Computational Linguistics, pages 2968–2978, Gyeongju, Republic of Korea. International Committee on Computational Linguistics.
Cite (Informal):
A Two Stage Adaptation Framework for Frame Detection via Prompt Learning (Mou et al., COLING 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.coling-1.263.pdf
Code
 xymou/frame_detection