Towards a Deep Multi-layered Dialectal Language Analysis: A Case Study of African-American English
This addresses the issue of language bias in NLP for AAE speakers, though it appears incremental as it builds on existing human-in-the-loop methods for dialectal analysis.
The paper tackles the problem of NLP models discriminating against African-American English (AAE) by analyzing AAE speakers' behavior through a human-in-the-loop approach, aiming to improve dialectal inclusivity and reduce disenfranchisement.
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.