Abstract
Millions of people around the world are sharing COVID-19 related information on social media platforms. Since not all the information shared on the social media is useful, a machine learning system to identify informative posts can help users in finding relevant information. In this paper, we present a BERT classifier system for W-NUT2020 Shared Task 2: Identification of Informative COVID-19 English Tweets. Further, we show that BERT exploits some easy signals to identify informative tweets, and adding simple patterns to uninformative tweets drastically degrades BERT performance. In particular, simply adding “10 deaths” to tweets in dev set, reduces BERT F1- score from 92.63 to 7.28. We also propose a simple data augmentation technique that helps in improving the robustness and generalization ability of the BERT classifier.- Anthology ID:
- 2020.wnut-1.64
- Volume:
- Proceedings of the Sixth Workshop on Noisy User-generated Text (W-NUT 2020)
- Month:
- November
- Year:
- 2020
- Address:
- Online
- Editors:
- Wei Xu, Alan Ritter, Tim Baldwin, Afshin Rahimi
- Venue:
- WNUT
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 440–443
- Language:
- URL:
- https://aclanthology.org/2020.wnut-1.64
- DOI:
- 10.18653/v1/2020.wnut-1.64
- Cite (ACL):
- Kumud Chauhan. 2020. NEU at WNUT-2020 Task 2: Data Augmentation To Tell BERT That Death Is Not Necessarily Informative. In Proceedings of the Sixth Workshop on Noisy User-generated Text (W-NUT 2020), pages 440–443, Online. Association for Computational Linguistics.
- Cite (Informal):
- NEU at WNUT-2020 Task 2: Data Augmentation To Tell BERT That Death Is Not Necessarily Informative (Chauhan, WNUT 2020)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-1/2020.wnut-1.64.pdf