Multi Output Learning using Task Wise Attention for Predicting Binary Properties of Tweets : Shared-Task-On-Fighting the COVID-19 Infodemic

Ayush Suhane, Shreyas Kowshik


Abstract
In this paper, we describe our system for the shared task on Fighting the COVID-19 Infodemic in the English Language. Our proposed architecture consists of a multi-output classification model for the seven tasks, with a task-wise multi-head attention layer for inter-task information aggregation. This was built on top of the Bidirectional Encoder Representations obtained from the RoBERTa Transformer. We were able to achieve a mean F1 score of 0.891 on the test data, leading us to the second position on the test-set leaderboard.
Anthology ID:
2021.nlp4if-1.16
Volume:
Proceedings of the Fourth Workshop on NLP for Internet Freedom: Censorship, Disinformation, and Propaganda
Month:
June
Year:
2021
Address:
Online
Editors:
Anna Feldman, Giovanni Da San Martino, Chris Leberknight, Preslav Nakov
Venue:
NLP4IF
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
110–114
Language:
URL:
https://aclanthology.org/2021.nlp4if-1.16
DOI:
10.18653/v1/2021.nlp4if-1.16
Bibkey:
Cite (ACL):
Ayush Suhane and Shreyas Kowshik. 2021. Multi Output Learning using Task Wise Attention for Predicting Binary Properties of Tweets : Shared-Task-On-Fighting the COVID-19 Infodemic. In Proceedings of the Fourth Workshop on NLP for Internet Freedom: Censorship, Disinformation, and Propaganda, pages 110–114, Online. Association for Computational Linguistics.
Cite (Informal):
Multi Output Learning using Task Wise Attention for Predicting Binary Properties of Tweets : Shared-Task-On-Fighting the COVID-19 Infodemic (Suhane & Kowshik, NLP4IF 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.nlp4if-1.16.pdf