Adversities are all you need: Classification of self-reported breast cancer posts on Twitter using Adversarial Fine-tuning

Adarsh Kumar, Ojasv Kamal, Susmita Mazumdar


Abstract
In this paper, we describe our system entry for Shared Task 8 at SMM4H-2021, which is on automatic classification of self-reported breast cancer posts on Twitter. In our system, we use a transformer-based language model fine-tuning approach to automatically identify tweets in the self-reports category. Furthermore, we involve a Gradient-based Adversarial fine-tuning to improve the overall model’s robustness. Our system achieved an F1-score of 0.8625 on the Development set and 0.8501 on the Test set in Shared Task-8 of SMM4H-2021.
Anthology ID:
2021.smm4h-1.22
Volume:
Proceedings of the Sixth Social Media Mining for Health (#SMM4H) Workshop and Shared Task
Month:
June
Year:
2021
Address:
Mexico City, Mexico
Venues:
NAACL | SMM4H
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
112–114
Language:
URL:
https://aclanthology.org/2021.smm4h-1.22
DOI:
10.18653/v1/2021.smm4h-1.22
Bibkey:
Cite (ACL):
Adarsh Kumar, Ojasv Kamal, and Susmita Mazumdar. 2021. Adversities are all you need: Classification of self-reported breast cancer posts on Twitter using Adversarial Fine-tuning. In Proceedings of the Sixth Social Media Mining for Health (#SMM4H) Workshop and Shared Task, pages 112–114, Mexico City, Mexico. Association for Computational Linguistics.
Cite (Informal):
Adversities are all you need: Classification of self-reported breast cancer posts on Twitter using Adversarial Fine-tuning (Kumar et al., SMM4H 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.smm4h-1.22.pdf
Data
BLUE