Leveraging Adapters for Improved Cross-lingual Transfer for Low-Resource Creole MT

Marcell Richard Fekete, Ernests Lavrinovics, Nathaniel Romney Robinson, Heather Lent, Raj Dabre, Johannes Bjerva


Abstract
———– EXTENDED ABSTRACT INTRODUCTION ———–Creole languages are low-resource languages, often genetically related to languages like English, French, and Portuguese, due to their linguistic histories with colonialism (DeGraff, 2003). As such, Creoles stand to benefit greatly from both data-efficient methods and transfer-learning from high-resource languages. At the same time, it has been observed by Lent et al. (2022b) that machine translation (MT) is a highly desired language technology by speakers of many Creoles. To this end, recent works have contributed new datasets, allowing for the development and evaluation of MT systems for Creoles (Robinson et al., 2024; Lent et al. 2024). In this work, we explore the use of the limited monolingual and parallel data for Creoles using parameter-efficient adaptation methods. Specifically, we compare the performance of different adapter architectures over the set of available benchmarks. We find adapters a promising approach for Creoles because they are parameter-efficient and have been shown to leverage transfer learning between related languages (Faisal and Anastasopoulos, 2022). While we perform experiments across multiple Creoles, we present only on Haitian Creole in this extended abstract. For future work, we aim to explore the potentials for leveraging other high-resourced languages for parameter-efficient transfer learning.
Anthology ID:
2024.mrl-1.17
Volume:
Proceedings of the Fourth Workshop on Multilingual Representation Learning (MRL 2024)
Month:
November
Year:
2024
Address:
Miami, Florida, USA
Editors:
Jonne Sälevä, Abraham Owodunni
Venue:
MRL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
212–215
Language:
URL:
https://aclanthology.org/2024.mrl-1.17
DOI:
Bibkey:
Cite (ACL):
Marcell Richard Fekete, Ernests Lavrinovics, Nathaniel Romney Robinson, Heather Lent, Raj Dabre, and Johannes Bjerva. 2024. Leveraging Adapters for Improved Cross-lingual Transfer for Low-Resource Creole MT. In Proceedings of the Fourth Workshop on Multilingual Representation Learning (MRL 2024), pages 212–215, Miami, Florida, USA. Association for Computational Linguistics.
Cite (Informal):
Leveraging Adapters for Improved Cross-lingual Transfer for Low-Resource Creole MT (Fekete et al., MRL 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.mrl-1.17.pdf