Cross-lingual Transfer Performance Variability in PaLI and Flamingo with Intermediate Task Data Size

Recently, although pre-trained language models have achieved great success on multilingual NLP (Natural Language Processing) tasks, the lack of training data on many tasks in low-resource languages still limits their performance. One effective way of solving that problem is to transfer knowledge from rich-resource languages to low-resource languages. However, many previous works on cross-lingual transfer rely heavily on the parallel corpus or translation models, which are often difficult to obtain. We propose a novel approach to conduct zero-shot cross-lingual transfer with a pre-trained model

Research goal: What is the impact of varying the size of intermediate task training data on zero-shot cross-lingual transfer performance for models like PaLI and Flamingo on the XTREME-R benchmark?

Autonomous synthesis report generated by Assignee Research. Tribunal consensus score: 7.9/10.