Deep Learning for Bias Detection: From Inception to Deployment
This work addresses the need for inclusive workplaces by providing a tool to identify bias in enterprise functions, though it is incremental as it applies existing deep learning methods to a new domain.
The authors tackled the problem of automatically detecting unconscious bias in enterprise content by proposing a deep learning model with transfer learning, achieving a general application through thorough evaluation on independent datasets.
To create a more inclusive workplace, enterprises are actively investing in identifying and eliminating unconscious bias (e.g., gender, race, age, disability, elitism and religion) across their various functions. We propose a deep learning model with a transfer learning based language model to learn from manually tagged documents for automatically identifying bias in enterprise content. We first pretrain a deep learning-based language-model using Wikipedia, then fine tune the model with a large unlabelled data set related with various types of enterprise content. Finally, a linear layer followed by softmax layer is added at the end of the language model and the model is trained on a labelled bias dataset consisting of enterprise content. The trained model is thoroughly evaluated on independent datasets to ensure a general application. We present the proposed method and its deployment detail in a real-world application.