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

• URL: http://arxiv.org/abs/2606.12708v1
• Date: Wed, 10 Jun 2026 21:55:02 GMT
• Title: AfriSUD: A Dependency Treebank Collection for Evaluating Models on African Languages
• Abstract summary: AfriSUD is the first large-scale collection of syntactically annotated treebanks for nine diverse African languages.<n>We evaluate a range of models on AfriSUD for part-of-speech tagging and dependency parsing.
• Score: 9.958060369042538
• License: http://creativecommons.org/licenses/by/4.0/
• 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.

Related papers

• AfroScope: A Framework for Studying the Linguistic Landscape of Africa [27.262469904340836]
  We introduce AfroScope, a unified framework for African LID, including AfroScope-Data and AfroScope-Models.<n>We propose a hierarchical classification approach that leverages Mirror-Serengeti, a specialized embedding model targeting 29 closely related or geographically proximate languages.<n>We analyze cross linguistic transfer and domain effects, offering guidance for building robust African LID systems.
  arXiv  Detail & Related papers  (2026-01-19T19:30:35Z)
• Mafoko: Structuring and Building Open Multilingual Terminologies for South African NLP [3.0720023574418622]
  We introduce the foundational Mafoko dataset, released under the equitable, Africa-centered NOODL framework.<n> Experiments show substantial improvements in the accuracy and domain-specific consistency of English-to-Tshivenda machine translation.
  arXiv  Detail & Related papers  (2025-08-05T15:00:02Z)
• Natural language processing for African languages [7.884789325654572]
  dissertation focuses on languages spoken in Sub-Saharan Africa where all the indigenous languages can be regarded as low-resourced.<n>We show that the quality of semantic representations learned in word embeddings does not only depend on the amount of data but on the quality of pre-training data.<n>We develop large scale human-annotated labelled datasets for 21 African languages in two impactful NLP tasks.
  arXiv  Detail & Related papers  (2025-06-30T22:26:36Z)
• Lugha-Llama: Adapting Large Language Models for African Languages [48.97516583523523]
  Large language models (LLMs) have achieved impressive results in a wide range of natural language applications.<n>We consider how to adapt LLMs to low-resource African languages.<n>We find that combining curated data from African languages with high-quality English educational texts results in a training mix that substantially improves the model's performance on these languages.
  arXiv  Detail & Related papers  (2025-04-09T02:25:53Z)
• Where Are We? Evaluating LLM Performance on African Languages [16.206469767073155]
  Africa's rich linguistic heritage remains underrepresented in NLP.<n>This paper integrates theoretical insights on Africa's language landscape with an empirical evaluation using Sahara.
  arXiv  Detail & Related papers  (2025-02-26T21:49:54Z)
• Assessing Dialect Fairness and Robustness of Large Language Models in Reasoning Tasks [68.33068005789116]
  We introduce ReDial, a benchmark containing 1.2K+ parallel query pairs in Standardized English and AAVE.<n>We evaluate widely used models, including GPT, Claude, Llama, Mistral, and the Phi model families.<n>Our work establishes a systematic and objective framework for analyzing LLM bias in dialectal queries.
  arXiv  Detail & Related papers  (2024-10-14T18:44:23Z)
• Natural Language Processing for Dialects of a Language: A Survey [56.93337350526933]
  State-of-the-art natural language processing (NLP) models are trained on massive training corpora, and report a superlative performance on evaluation datasets.<n>This survey delves into an important attribute of these datasets: the dialect of a language.<n>Motivated by the performance degradation of NLP models for dialectal datasets and its implications for the equity of language technologies, we survey past research in NLP for dialects in terms of datasets, and approaches.
  arXiv  Detail & Related papers  (2024-01-11T03:04:38Z)
• AfroBench: How Good are Large Language Models on African Languages? [55.35674466745322]
  AfroBench is a benchmark for evaluating the performance of LLMs across 64 African languages.<n>AfroBench consists of nine natural language understanding datasets, six text generation datasets, six knowledge and question answering tasks, and one mathematical reasoning task.
  arXiv  Detail & Related papers  (2023-11-14T08:10:14Z)
• Quantifying the Dialect Gap and its Correlates Across Languages [69.18461982439031]
  This work will lay the foundation for furthering the field of dialectal NLP by laying out evident disparities and identifying possible pathways for addressing them through mindful data collection.
  arXiv  Detail & Related papers  (2023-10-23T17:42:01Z)
• Low-Resource Language Modelling of South African Languages [6.805575417034369]
  We evaluate the performance of open-vocabulary language models on low-resource South African languages. We evaluate different variants of n-gram models, feedforward neural networks, recurrent neural networks (RNNs) and Transformers on small-scale datasets. Overall, well-regularized RNNs give the best performance across two isiZulu and one Sepedi datasets.
  arXiv  Detail & Related papers  (2021-04-01T21:27:27Z)
• MasakhaNER: Named Entity Recognition for African Languages [48.34339599387944]
  We create the first large publicly available high-quality dataset for named entity recognition in ten African languages. We detail characteristics of the languages to help researchers understand the challenges that these languages pose for NER.
  arXiv  Detail & Related papers  (2021-03-22T13:12:44Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.