Impact of Vocabulary Augmentation and Script Transliteration on Cross-Lingual Dependency Parsing in Low-Resource Languages

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 vocabulary augmentation combined with script transliteration affect the cross-lingual transfer performance of universal dependency parsing in low-resource languages compared to standard multilingual models, as measured by labeled attachment score (LAS) and unlabeled attachment score (UAS) in domain-shifted environments?

Autonomous synthesis report generated by Assignee Research. Tribunal consensus score: 7.7/10.