ML_LTU at SemEval-2022 Task 4: T5 Towards Identifying Patronizing and Condescending Language
Tosin Adewumi, Lama Alkhaled, Hamam Mokayed, Foteini Liwicki, Marcus Liwicki
Abstract
This paper describes the system used by the Machine Learning Group of LTU in subtask 1 of the SemEval-2022 Task 4: Patronizing and Condescending Language (PCL) Detection. Our system consists of finetuning a pretrained text-to-text transfer transformer (T5) and innovatively reducing its out-of-class predictions. The main contributions of this paper are 1) the description of the implementation details of the T5 model we used, 2) analysis of the successes & struggles of the model in this task, and 3) ablation studies beyond the official submission to ascertain the relative importance of data split. Our model achieves an F1 score of 0.5452 on the official test set.- Anthology ID:
- 2022.semeval-1.64
- Volume:
- Proceedings of the 16th International Workshop on Semantic Evaluation (SemEval-2022)
- Month:
- July
- Year:
- 2022
- Address:
- Seattle, United States
- Venue:
- SemEval
- SIG:
- SIGLEX
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 473–478
- Language:
- URL:
- https://aclanthology.org/2022.semeval-1.64
- DOI:
- 10.18653/v1/2022.semeval-1.64
- Cite (ACL):
- Tosin Adewumi, Lama Alkhaled, Hamam Mokayed, Foteini Liwicki, and Marcus Liwicki. 2022. ML_LTU at SemEval-2022 Task 4: T5 Towards Identifying Patronizing and Condescending Language. In Proceedings of the 16th International Workshop on Semantic Evaluation (SemEval-2022), pages 473–478, Seattle, United States. Association for Computational Linguistics.
- Cite (Informal):
- ML_LTU at SemEval-2022 Task 4: T5 Towards Identifying Patronizing and Condescending Language (Adewumi et al., SemEval 2022)
- PDF:
- https://preview.aclanthology.org/starsem-semeval-split/2022.semeval-1.64.pdf