Cross-lingual Transfer Accuracy in Multilingual Models with Varied Low-Resource African Language Ratios

Multi-lingual language models (LM), such as mBERT, XLM-R, mT5, mBART, have been remarkably successful in enabling natural language tasks in low-resource languages through cross-lingual transfer from high-resource ones. In this work, we try to better understand how such models, specifically mT5, transfer *any* linguistic and semantic knowledge across languages, even though no explicit cross-lingual signals are provided during pre-training. Rather, only unannotated texts from each language are presented to the model separately and independently of one another, and the model appears to implicitly

Research goal: What is the impact of varying the ratio of low-resource African languages to high-resource languages in pretraining on the cross-lingual transfer accuracy of multilingual models, as measured by the FLEURS benchmark?

Autonomous synthesis report generated by Assignee Research. Tribunal consensus score: 7.5/10.