Recent studies show that NLP models trained on standard English texts tend to produce biased outcomes against underrepresented English varieties. In this work, we conduct a pioneering study of the English variety use of African American English (AAE) in NLI task. First, we propose CodeSwitch, a greedy unidirectional morphosyntactically-informed rule-based translation method for data augmentation. Next, we use CodeSwitch to present a preliminary study to determine if demographic language features do in fact influence models to produce false predictions. Then, we conduct experiments on two popular datasets and propose two simple, yet effective and generalizable debiasing methods. Our findings show that NLI models (e.g. BERT) trained under our proposed frameworks outperform traditional large language models while maintaining or even improving the prediction performance. In addition, we intend to release CodeSwitch, in hopes of promoting dialectal language diversity in training data to both reduce the discriminatory societal impacts and improve model robustness of downstream NLP tasks.

Currently, natural language processing (NLP) models proliferate language discrimination leading to potentially harmful societal impacts as a result of biased outcomes. For example, part-of-speech taggers trained on Mainstream American English (MAE) produce non-interpretable results when applied to African American English (AAE) as a result of language features not seen during training. In this work, we incorporate a human-in-the-loop paradigm to gain a better understanding of AAE speakers’ behavior and their language use, and highlight the need for dialectal language inclusivity so that native AAE speakers can extensively interact with NLP systems while reducing feelings of disenfranchisement.

Recently there are increasing concerns about the fairness of Artificial Intelligence (AI) in real-world applications such as computer vision and recommendations. For example, recognition algorithms in computer vision are unfair to black people such as poorly detecting their faces and inappropriately identifying them as “gorillas”. As one crucial application of AI, dialogue systems have been extensively applied in our society. They are usually built with real human conversational data; thus they could inherit some fairness issues which are held in the real world. However, the fairness of dialogue systems has not been well investigated. In this paper, we perform a pioneering study about the fairness issues in dialogue systems. In particular, we construct a benchmark dataset and propose quantitative measures to understand fairness in dialogue models. Our studies demonstrate that popular dialogue models show significant prejudice towards different genders and races. Besides, to mitigate the bias in dialogue systems, we propose two simple but effective debiasing methods. Experiments show that our methods can reduce the bias in dialogue systems significantly. The dataset and the implementation are released to foster fairness research in dialogue systems.