| Autor: |
Ghanbarzadeh, Somayeh, Huang, Yan, Palangi, Hamid, Moreno, Radames Cruz, Khanpour, Hamed |
| Rok vydání: |
2023 |
| Předmět: |
|
| Zdroj: |
ACL 2023 |
| Druh dokumentu: |
Working Paper |
| Popis: |
Recent studies have revealed that the widely-used Pre-trained Language Models (PLMs) propagate societal biases from the large unmoderated pre-training corpora. Existing solutions require debiasing training processes and datasets for debiasing, which are resource-intensive and costly. Furthermore, these methods hurt the PLMs' performance on downstream tasks. In this study, we propose Gender-tuning, which debiases the PLMs through fine-tuning on downstream tasks' datasets. For this aim, Gender-tuning integrates Masked Language Modeling (MLM) training objectives into fine-tuning's training process. Comprehensive experiments show that Gender-tuning outperforms the state-of-the-art baselines in terms of average gender bias scores in PLMs while improving PLMs' performance on downstream tasks solely using the downstream tasks' dataset. Also, Gender-tuning is a deployable debiasing tool for any PLM that works with original fine-tuning. |
| Databáze: |
arXiv |
| Externí odkaz: |
|
