Exploration of Contrastive Learning Strategies toward more Robust Stance Detection

Udhaya Kumar Rajendran, Amine Trabelsi


Abstract
Stance Detection is the task of identifying the position of an author of a text towards an issue or a target. Previous studies on Stance Detection indicate that the existing systems are non-robust to the variations and errors in input sentences. Our proposed methodology uses Contrastive Learning to learn sentence representations by bringing semantically similar sentences and sentences implying the same stance closer to each other in the embedding space. We compare our approach to a pretrained transformer model directly finetuned with the stance datasets. We use char-level and word-level adversarial perturbation attacks to measure the resilience of the models and we show that our approach achieves better performances and is more robust to the different adversarial perturbations introduced to the test data. The results indicate that our approach performs better on small-sized and class-imbalanced stance datasets.
Anthology ID:
2023.wassa-1.37
Volume:
Proceedings of the 13th Workshop on Computational Approaches to Subjectivity, Sentiment, & Social Media Analysis
Month:
July
Year:
2023
Address:
Toronto, Canada
Editors:
Jeremy Barnes, Orphée De Clercq, Roman Klinger
Venue:
WASSA
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
431–440
Language:
URL:
https://aclanthology.org/2023.wassa-1.37
DOI:
10.18653/v1/2023.wassa-1.37
Bibkey:
Cite (ACL):
Udhaya Kumar Rajendran and Amine Trabelsi. 2023. Exploration of Contrastive Learning Strategies toward more Robust Stance Detection. In Proceedings of the 13th Workshop on Computational Approaches to Subjectivity, Sentiment, & Social Media Analysis, pages 431–440, Toronto, Canada. Association for Computational Linguistics.
Cite (Informal):
Exploration of Contrastive Learning Strategies toward more Robust Stance Detection (Rajendran & Trabelsi, WASSA 2023)
Copy Citation:
PDF:
https://aclanthology.org/2023.wassa-1.37.pdf
Video:
 https://aclanthology.org/2023.wassa-1.37.mp4