Please use this identifier to cite or link to this item: http://hdl.handle.net/10397/97879
PIRA download icon_1.1View/Download Full Text
Title: Exploring a unified sequence-to-sequence transformer for medical product safety monitoring in social media
Authors: Raval, S
Sedghamiz, H
Santus, E
Alhanai, T
Ghassemi, M
Chersoni, E 
Issue Date: Nov-2021
Source: In MF Moens, X Huang, L Specia & SW Yih (Eds.), Findings of the Association for Computational Linguistics: EMNLP 2021, p. 3534–3546, Punta Cana, Dominican Republic. Association for Computational Linguistics, 2021
Abstract: Adverse Events (AE) are harmful events resulting from the use of medical products. Although social media may be crucial for early AE detection, the sheer scale of this data makes it logistically intractable to analyze using human agents, with NLP representing the only low-cost and scalable alternative. In this paper, we frame AE Detection and Extraction as a sequence-to-sequence problem using the T5 model architecture and achieve strong performance improvements over the baselines on several English benchmarks (F1 = 0.71, 12.7% relative improvement for AE Detection; Strict F1 = 0.713, 12.4% relative improvement for AE Extraction). Motivated by the strong commonalities between AE tasks, the class imbalance in AE benchmarks, and the linguistic and structural variety typical of social media texts, we propose a new strategy for multi-task training that accounts, at the same time, for task and dataset characteristics. Our approach increases model robustness, leading to further performance gains. Finally, our framework shows some language transfer capabilities, obtaining higher performance than Multilingual BERT in zero-shot learning on French data.
Publisher: Association for Computational Linguistics
ISBN: 978-1-955917-10-0
DOI: 10.18653/v1/2021.findings-emnlp.300
Description: Findings of the Association for Computational Linguistics: EMNLP 2021, Punta Cana, Dominican Republic, November 7–11, 2021
Rights: ©2021 Association for Computational Linguistics
Materials published in or after 2016 are licensed on a Creative Commons Attribution 4.0 International License. (https://creativecommons.org/licenses/by/4.0/)
The following publication Shivam Raval, Hooman Sedghamiz, Enrico Santus, Tuka Alhanai, Mohammad Ghassemi, and Emmanuele Chersoni. 2021. Exploring a Unified Sequence-To-Sequence Transformer for Medical Product Safety Monitoring in Social Media. In Findings of the Association for Computational Linguistics: EMNLP 2021, pages 3534–3546, Punta Cana, Dominican Republic. Association for Computational Linguistics is available at https://aclanthology.org/2021.findings-emnlp.300/.
Appears in Collections:Conference Paper

Files in This Item:
File Description SizeFormat 
Chersoni_Exploring_Unified_Sequence-To-Sequence.pdf446.43 kBAdobe PDFView/Open
Open Access Information
Status open access
File Version Version of Record
Access
View full-text via PolyU eLinks SFX Query
Show full item record

Page views

56
Citations as of Mar 24, 2024

Downloads

19
Citations as of Mar 24, 2024

Google ScholarTM

Check

Altmetric


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.