Combining language models and linguistic information to label entities in memes
- Publication type
- P1
- Publication status
- Published
- Authors
- Singh, P., Maladry, A, & Lefever, E.
- Series
- Proceedings of the Workshop on Combating Online Hostile Posts in Regional Languages during Emergency Situations
- Pagination
- 35-42
- Publisher
- Association for Computational Linguistics (ACL)
- Conference
- Second Workshop on Combating Online Hostile Posts in Regional Languages during Emergency Situation (Dublin, Ireland)
- Download
- (.pdf)
- View in Biblio
- (externe link)
Abstract
This paper describes the system we developed for the shared task “Hero, Villain and Victim: Dissecting harmful memes for Semantic role labeling of entities” organized in the frame- work of the Second Workshop on Combating Online Hostile Posts in Regional Languages during Emergency Situation (Constraint 2022). We present an ensemble approach combining transformer-based models and linguistic information, such as the presence of irony and implicit sentiment associated to the target named entities. The ensemble system obtains promising classification scores, with a macro F-score of 55%, resulting in a third place finish in the competition.