Papers › ANGOFA: Leveraging OFA Embedding Initialization and Synthetic Data for Angolan Language Model

ANGOFA: Leveraging OFA Embedding Initialization and Synthetic Data for Angolan Language Model

3 Apr 2024arXiv:2404.02534archive 2025-07-28

Osvaldo Luamba Quinjica, David Ifeoluwa Adelani

In recent years, the development of pre-trained language models (PLMs) has gained momentum, showcasing their capacity to transcend linguistic barriers and facilitate knowledge transfer across diverse languages. However, this progress has predominantly bypassed the inclusion of very-low resource languages, creating a notable void in the multilingual landscape. This paper addresses this gap by introducing four tailored PLMs specifically finetuned for Angolan languages, employing a Multilingual Adaptive Fine-tuning (MAFT) approach. In this paper, we survey the role of informed embedding initialization and synthetic data in enhancing the performance of MAFT models in downstream tasks. We improve baseline over SOTA AfroXLMR-base (developed through MAFT) and OFA (an effective embedding initialization) by 12.3 and 3.8 points respectively.

PaperPDFCode

Code

zuela-ai/angofa officialmentioned in paperpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Language ModelingLanguage ModellingTransfer Learning

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

OFA

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections