AfriSUD: A Dependency Treebank Collection for Evaluating Models on African Languages

Researchers introduced AfriSUD, the first large-scale collection of syntactically annotated treebanks for nine African languages, using the Surface-Syntactic Universal Dependencies framework to capture typological features like agglutination and tone. The community-led effort provides native-speaker verified data to address the underrepresentation of African languages in NLP resources. Evaluations of multiple models for part-of-speech tagging and dependency parsing revealed a significant syntax gap, indicating that current architectures struggle to fully capture the structural diversity of African-language syntax.

arXiv:2606.12708v1 Announce Type: new Abstract: Despite their linguistic diversity and global significance, African languages remain underrepresented in research and resources to support NLP. We aim to bridge this gap by introducing AfriSUD, the first large-scale collection of syntactically annotated treebanks for nine diverse African languages spanning major language families and regions across Sub-Saharan Africa. Using the Surface-Syntactic Universal Dependencies SUD framework, our community-led effort provides high-quality, native-speaker verified data that capture typological key features such as agglutination and tone. We evaluate a range of models on AfriSUD for part-of-speech tagging and dependency parsing including non-transformer baselines, multilingual pretrained encoders, and LLMs. Our results reveal a significant syntax gap, where models still show clear limitations across the nine languages, suggesting that existing architectures may not fully capture the structural diversity of African-language syntax.