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

Marcell Fekete, Ernests Lavrinovics, Nathaniel R. Robinson, Heather Lent, Raj Dabre, Johannes Bjerva

Publikation: Bidrag til bog/antologi/rapport/konference proceedingKonferenceabstrakt i proceedingForskningpeer review

Abstract

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.
OriginalsprogEngelsk
TitelProceedings of the Fourth Workshop on Multilingual Representation Learning : (MRL 2024)
ForlagAssociation for Computational Linguistics
Publikationsdatonov. 2024
Sider212-215
ISBN (Elektronisk)979-8-89176-184-1
StatusUdgivet - nov. 2024
BegivenhedThe 4th Workshop on Multilingual Representation Learning - Miami, USA
Varighed: 16 nov. 202416 nov. 2024
Konferencens nummer: 4
https://sigtyp.github.io/ws2024-mrl.html

Workshop

WorkshopThe 4th Workshop on Multilingual Representation Learning
Nummer4
Land/OmrådeUSA
ByMiami
Periode16/11/202416/11/2024
Internetadresse

Fingeraftryk

Dyk ned i forskningsemnerne om 'Leveraging Adapters for Improved Cross-lingual Transfer for Low-Resource Creole MT'. Sammen danner de et unikt fingeraftryk.

Citationsformater