Abstract
Existing large language models (LLMs) that mainly focus on Standard American English (SAE) often lead to significantly worse performance when being applied to other English dialects. While existing mitigations tackle discrepancies for individual target dialects, they assume access to high-accuracy dialect identification systems. The boundaries between dialects are inherently flexible, making it difficult to categorize language into discrete predefined categories. In this paper, we propose DADA (Dialect Adaptation via Dynamic Aggregation), a modular approach to imbue SAE-trained models with multi-dialectal robustness by composing adapters which handle specific linguistic features. The compositional architecture of DADA allows for both targeted adaptation to specific dialect variants and simultaneous adaptation to various dialects. We show that DADA is effective for both single task and instruction finetuned language models, offering an extensible and interpretable framework for adapting existing LLMs to different English dialects.- Anthology ID:
- 2023.emnlp-main.850
- Volume:
- Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing
- Month:
- December
- Year:
- 2023
- Address:
- Singapore
- Editors:
- Houda Bouamor, Juan Pino, Kalika Bali
- Venue:
- EMNLP
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 13776–13793
- Language:
- URL:
- https://aclanthology.org/2023.emnlp-main.850
- DOI:
- 10.18653/v1/2023.emnlp-main.850
- Cite (ACL):
- Yanchen Liu, William Held, and Diyi Yang. 2023. DADA: Dialect Adaptation via Dynamic Aggregation of Linguistic Rules. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 13776–13793, Singapore. Association for Computational Linguistics.
- Cite (Informal):
- DADA: Dialect Adaptation via Dynamic Aggregation of Linguistic Rules (Liu et al., EMNLP 2023)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-2/2023.emnlp-main.850.pdf