Semi-supervised Multi-task Learning for Multi-label Fine-grained Sexism Classification

Harika Abburi, Pulkit Parikh, Niyati Chhaya, Vasudeva Varma


Abstract
Sexism, a form of oppression based on one’s sex, manifests itself in numerous ways and causes enormous suffering. In view of the growing number of experiences of sexism reported online, categorizing these recollections automatically can assist the fight against sexism, as it can facilitate effective analyses by gender studies researchers and government officials involved in policy making. In this paper, we investigate the fine-grained, multi-label classification of accounts (reports) of sexism. To the best of our knowledge, we work with considerably more categories of sexism than any published work through our 23-class problem formulation. Moreover, we propose a multi-task approach for fine-grained multi-label sexism classification that leverages several supporting tasks without incurring any manual labeling cost. Unlabeled accounts of sexism are utilized through unsupervised learning to help construct our multi-task setup. We also devise objective functions that exploit label correlations in the training data explicitly. Multiple proposed methods outperform the state-of-the-art for multi-label sexism classification on a recently released dataset across five standard metrics.
Anthology ID:
2020.coling-main.511
Volume:
Proceedings of the 28th International Conference on Computational Linguistics
Month:
December
Year:
2020
Address:
Barcelona, Spain (Online)
Venue:
COLING
SIG:
Publisher:
International Committee on Computational Linguistics
Note:
Pages:
5810–5820
Language:
URL:
https://aclanthology.org/2020.coling-main.511
DOI:
10.18653/v1/2020.coling-main.511
Bibkey:
Cite (ACL):
Harika Abburi, Pulkit Parikh, Niyati Chhaya, and Vasudeva Varma. 2020. Semi-supervised Multi-task Learning for Multi-label Fine-grained Sexism Classification. In Proceedings of the 28th International Conference on Computational Linguistics, pages 5810–5820, Barcelona, Spain (Online). International Committee on Computational Linguistics.
Cite (Informal):
Semi-supervised Multi-task Learning for Multi-label Fine-grained Sexism Classification (Abburi et al., COLING 2020)
Copy Citation:
PDF:
https://aclanthology.org/2020.coling-main.511.pdf
Code
 harikavuppala1a/semisupervised_multitask_learning