BOUN-TABI@SMM4H’22: Text-to-Text Adverse Drug Event Extraction with Data Balancing and Prompting

Gökçe Uludoğan, Zeynep Yirmibeşoğlu


Abstract
This paper describes models developed for the Social Media Mining for Health 2022 Shared Task. We participated in two subtasks: classification of English tweets reporting adverse drug events (ADE) (Task 1a) and extraction of ADE spans in such tweets (Task 1b). We developed two separate systems based on the T5 model, viewing these tasks as sequence-to-sequence problems. To address the class imbalance, we made use of data balancing via over- and undersampling on both tasks. For the ADE extraction task, we explored prompting to further benefit from the T5 model and its formulation. Additionally, we built an ensemble model, utilizing both balanced and prompted models. The proposed models outperformed the current state-of-the-art, with an F1 score of 0.655 on ADE classification and a Partial F1 score of 0.527 on ADE extraction.
Anthology ID:
2022.smm4h-1.9
Volume:
Proceedings of The Seventh Workshop on Social Media Mining for Health Applications, Workshop & Shared Task
Month:
October
Year:
2022
Address:
Gyeongju, Republic of Korea
Editors:
Graciela Gonzalez-Hernandez, Davy Weissenbacher
Venue:
SMM4H
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
31–34
Language:
URL:
https://aclanthology.org/2022.smm4h-1.9
DOI:
Bibkey:
Cite (ACL):
Gökçe Uludoğan and Zeynep Yirmibeşoğlu. 2022. BOUN-TABI@SMM4H’22: Text-to-Text Adverse Drug Event Extraction with Data Balancing and Prompting. In Proceedings of The Seventh Workshop on Social Media Mining for Health Applications, Workshop & Shared Task, pages 31–34, Gyeongju, Republic of Korea. Association for Computational Linguistics.
Cite (Informal):
BOUN-TABI@SMM4H’22: Text-to-Text Adverse Drug Event Extraction with Data Balancing and Prompting (Uludoğan & Yirmibeşoğlu, SMM4H 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.smm4h-1.9.pdf