CAISA at WASSA 2022: Adapter-Tuning for Empathy Prediction

Allison Lahnala, Charles Welch, Lucie Flek


Abstract
We build a system that leverages adapters, a light weight and efficient method for leveraging large language models to perform the task Em- pathy and Distress prediction tasks for WASSA 2022. In our experiments, we find that stacking our empathy and distress adapters on a pre-trained emotion lassification adapter performs best compared to full fine-tuning approaches and emotion feature concatenation. We make our experimental code publicly available
Anthology ID:
2022.wassa-1.31
Volume:
Proceedings of the 12th Workshop on Computational Approaches to Subjectivity, Sentiment & Social Media Analysis
Month:
May
Year:
2022
Address:
Dublin, Ireland
Editors:
Jeremy Barnes, Orphée De Clercq, Valentin Barriere, Shabnam Tafreshi, Sawsan Alqahtani, João Sedoc, Roman Klinger, Alexandra Balahur
Venue:
WASSA
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
280–285
Language:
URL:
https://aclanthology.org/2022.wassa-1.31
DOI:
10.18653/v1/2022.wassa-1.31
Bibkey:
Cite (ACL):
Allison Lahnala, Charles Welch, and Lucie Flek. 2022. CAISA at WASSA 2022: Adapter-Tuning for Empathy Prediction. In Proceedings of the 12th Workshop on Computational Approaches to Subjectivity, Sentiment & Social Media Analysis, pages 280–285, Dublin, Ireland. Association for Computational Linguistics.
Cite (Informal):
CAISA at WASSA 2022: Adapter-Tuning for Empathy Prediction (Lahnala et al., WASSA 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.wassa-1.31.pdf
Video:
 https://aclanthology.org/2022.wassa-1.31.mp4
Code
 caisa-lab/wassa-empathy-adapters
Data
CARER