Abstract
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.- Anthology ID:
- 2022.hcinlp-1.8
- Volume:
- Proceedings of the Second Workshop on Bridging Human--Computer Interaction and Natural Language Processing
- Month:
- July
- Year:
- 2022
- Address:
- Seattle, Washington
- Editors:
- Su Lin Blodgett, Hal Daumé III, Michael Madaio, Ani Nenkova, Brendan O'Connor, Hanna Wallach, Qian Yang
- Venue:
- HCINLP
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 55–63
- Language:
- URL:
- https://aclanthology.org/2022.hcinlp-1.8
- DOI:
- 10.18653/v1/2022.hcinlp-1.8
- Cite (ACL):
- Jamell Dacon. 2022. Towards a Deep Multi-layered Dialectal Language Analysis: A Case Study of African-American English. In Proceedings of the Second Workshop on Bridging Human--Computer Interaction and Natural Language Processing, pages 55–63, Seattle, Washington. Association for Computational Linguistics.
- Cite (Informal):
- Towards a Deep Multi-layered Dialectal Language Analysis: A Case Study of African-American English (Dacon, HCINLP 2022)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-4/2022.hcinlp-1.8.pdf