Reinforcement Guided Multi-Task Learning Framework for Low-Resource Stereotype Detection

Rajkumar Pujari, Erik Oveson, Priyanka Kulkarni, Elnaz Nouri


Abstract
As large Pre-trained Language Models (PLMs) trained on large amounts of data in an unsupervised manner become more ubiquitous, identifying various types of bias in the text has come into sharp focus. Existing ‘Stereotype Detection’ datasets mainly adopt a diagnostic approach toward large PLMs. Blodgett et. al. (2021) show that there are significant reliability issues with the existing benchmark datasets. Annotating a reliable dataset requires a precise understanding of the subtle nuances of how stereotypes manifest in text. In this paper, we annotate a focused evaluation set for ‘Stereotype Detection’ that addresses those pitfalls by de-constructing various ways in which stereotypes manifest in text. Further, we present a multi-task model that leverages the abundance of data-rich neighboring tasks such as hate speech detection, offensive language detection, misogyny detection, etc., to improve the empirical performance on ‘Stereotype Detection’. We then propose a reinforcement-learning agent that guides the multi-task learning model by learning to identify the training examples from the neighboring tasks that help the target task the most. We show that the proposed models achieve significant empirical gains over existing baselines on all the tasks.
Anthology ID:
2022.acl-long.462
Volume:
Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
Month:
May
Year:
2022
Address:
Dublin, Ireland
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
6703–6712
Language:
URL:
https://aclanthology.org/2022.acl-long.462
DOI:
10.18653/v1/2022.acl-long.462
Bibkey:
Cite (ACL):
Rajkumar Pujari, Erik Oveson, Priyanka Kulkarni, and Elnaz Nouri. 2022. Reinforcement Guided Multi-Task Learning Framework for Low-Resource Stereotype Detection. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 6703–6712, Dublin, Ireland. Association for Computational Linguistics.
Cite (Informal):
Reinforcement Guided Multi-Task Learning Framework for Low-Resource Stereotype Detection (Pujari et al., ACL 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.acl-long.462.pdf
Video:
 https://aclanthology.org/2022.acl-long.462.mp4
Code
 pujari-rajkumar/rl-guided-multitask-learning
Data
CrowS-PairsHate SpeechHate Speech and Offensive LanguageStereoSet