Condensing Multilingual Knowledge with Lightweight Language-Specific Modules

Haoran Xu, Weiting Tan, Shuyue Li, Yunmo Chen, Benjamin Van Durme, Philipp Koehn, Kenton Murray

Abstract
Incorporating language-specific (LS) modules or Mixture-of-Experts (MoE) are proven methods to boost performance in multilingual model performance, but the scalability of these approaches to hundreds of languages or experts tends to be hard to manage. We present Language-specific Matrix Synthesis (LMS), a novel method that addresses the issue. LMS utilizes parameter-efficient and lightweight modules, reducing the number of parameters while outperforming existing methods, e.g., +1.73 BLEU over Switch Transformer on OPUS-100 multilingual translation. Additionally, we introduce Fuse Distillation (FD) to condense multilingual knowledge from multiple LS modules into a single shared module, improving model inference and storage efficiency. Our approach demonstrates superior scalability and performance compared to state-of-the-art methods.
Anthology ID:
2023.emnlp-main.97
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:
1575–1587
Language:
URL:
https://aclanthology.org/2023.emnlp-main.97
DOI:
10.18653/v1/2023.emnlp-main.97
Bibkey:
Cite (ACL):
Haoran Xu, Weiting Tan, Shuyue Li, Yunmo Chen, Benjamin Van Durme, Philipp Koehn, and Kenton Murray. 2023. Condensing Multilingual Knowledge with Lightweight Language-Specific Modules. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 1575–1587, Singapore. Association for Computational Linguistics.
Cite (Informal):
Condensing Multilingual Knowledge with Lightweight Language-Specific Modules (Xu et al., EMNLP 2023)
Copy Citation:
PDF:
https://preview.aclanthology.org/dois-2013-emnlp/2023.emnlp-main.97.pdf
PDF Search