shefnlp at SemEval-2023 Task 10: Compute-Efficient Category Adapters

Thomas Pickard, Tyler Loakman, Mugdha Pandya

Abstract
As social media platforms grow, so too does the volume of hate speech and negative sentiment expressed towards particular social groups. In this paper, we describe our approach to SemEval-2023 Task 10, involving the detection and classification of online sexism (abuse directed towards women), with fine-grained categorisations intended to facilitate the development of a more nuanced understanding of the ideologies and processes through which online sexism is expressed. We experiment with several approaches involving language model finetuning, class-specific adapters, and pseudo-labelling. Our best-performing models involve the training of adapters specific to each subtask category (combined via fusion layers) using a weighted loss function, in addition to performing naive pseudo-labelling on a large quantity of unlabelled data. We successfully outperform the baseline models on all 3 subtasks, placing 56th (of 84) on Task A, 43rd (of 69) on Task B,and 37th (of 63) on Task C.
Anthology ID:
2023.semeval-1.147
Volume:
Proceedings of the 17th International Workshop on Semantic Evaluation (SemEval-2023)
Month:
July
Year:
2023
Address:
Toronto, Canada
Editors:
Atul Kr. Ojha, A. Seza Doğruöz, Giovanni Da San Martino, Harish Tayyar Madabushi, Ritesh Kumar, Elisa Sartori
Venue:
SemEval
SIG:
SIGLEX
Publisher:
Association for Computational Linguistics
Note:
Pages:
1069–1075
Language:
URL:
https://aclanthology.org/2023.semeval-1.147
DOI:
10.18653/v1/2023.semeval-1.147
Bibkey:
Cite (ACL):
Thomas Pickard, Tyler Loakman, and Mugdha Pandya. 2023. shefnlp at SemEval-2023 Task 10: Compute-Efficient Category Adapters. In Proceedings of the 17th International Workshop on Semantic Evaluation (SemEval-2023), pages 1069–1075, Toronto, Canada. Association for Computational Linguistics.
Cite (Informal):
shefnlp at SemEval-2023 Task 10: Compute-Efficient Category Adapters (Pickard et al., SemEval 2023)
Copy Citation:
PDF:
https://preview.aclanthology.org/dois-2013-emnlp/2023.semeval-1.147.pdf
PDF Search