Performance of Hybrid Batch-Trained Multilingual Models on XLM-R for Low-Resource Languages in Cross-Lingual Retrieval

Pretrained multilingual language models have become a common tool in transferring NLP capabilities to low-resource languages, often with adaptations. In this work, we study the performance, extensibility, and interaction of two such adaptations: vocabulary augmentation and script transliteration. Our evaluations on part-of-speech tagging, universal dependency parsing, and named entity recognition in nine diverse low-resource languages uphold the viability of these approaches while raising new questions around how to optimally adapt multilingual models to low-resource settings.

Research goal: How does the performance of hybrid batch-trained multilingual models on the XLM-R benchmark vary when evaluated on low-resource languages compared to high-resource languages, and what are the implications for cross-lingual retrieval tasks?

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