Bipol: A Novel Multi-Axes Bias Evaluation Metric with Explainability for NLP
This addresses the challenge of harmful bias in online data used for training ML models, though it appears incremental as it builds on existing SotA architectures for bias detection.
The researchers tackled the problem of measuring social bias in text data by introducing Bipol, a novel multi-axes bias evaluation metric with explainability, which achieved evaluation on two popular NLP datasets (COPA and SQUAD) and included a large publicly available dataset of nearly 2 million labeled samples for bias detection.
We introduce bipol, a new metric with explainability, for estimating social bias in text data. Harmful bias is prevalent in many online sources of data that are used for training machine learning (ML) models. In a step to address this challenge we create a novel metric that involves a two-step process: corpus-level evaluation based on model classification and sentence-level evaluation based on (sensitive) term frequency (TF). After creating new models to detect bias along multiple axes using SotA architectures, we evaluate two popular NLP datasets (COPA and SQUAD). As additional contribution, we created a large dataset (with almost 2 million labelled samples) for training models in bias detection and make it publicly available. We also make public our codes.