LinguaTriage: Cross-Lingual Transfer and African Language Pretraining for Low-Resource Medical Triage in Lingala

Patrick S. Tenga, Mohamed A. Kholief
Proceedings of IndabaX Nigeria 2026: Building Scalable AI That Works: From Research to Deployment in Resource-Constrained Environments, PMLR 319:87-100, 2026.

Abstract

We introduce LinguaTriage, the first medical triage classification system for Lingala, a Bantu language of Central Africa spoken by over 45 million people with no prior supervised NLP benchmarks. Working from a 616-sample dataset of annotated symptom descriptions across three urgency levels, we develop a targeted augmentation pipeline and evaluate three architectures: fine-tuned XLM-RoBERTa (XLM-RFT), a two-stage cross-lingual transfer system (XLM-RCL), and fine-tuned AfriBERTa-Large (AfriBERTaFT). AfriBERTaFT achieves macro-F1 of 0.974 and perfect Emergency recall (1.00) on the internal test set. Mixing just 100 in-domain examples into training improves external accuracy from near-chance to 79%, demonstrating that minimal target-domain exposure far outweighs architectural choices for generalisation.

Cite this Paper

BibTeX
@InProceedings{pmlr-v319-tenga26a, title = {{LinguaTriage}: Cross-Lingual Transfer and African Language Pretraining for Low-Resource Medical Triage in {Lingala}}, author = {Tenga, Patrick S. and Kholief, Mohamed A.}, booktitle = {Proceedings of IndabaX Nigeria 2026: Building Scalable AI That Works: From Research to Deployment in Resource-Constrained Environments}, pages = {87--100}, year = {2026}, editor = {Folorunso, Sakinat and Ogundokun, Roseline and Oladipo, Francisca}, volume = {319}, series = {Proceedings of Machine Learning Research}, month = {11--14 May}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v319/main/assets/tenga26a/tenga26a.pdf}, url = {https://proceedings.mlr.press/v319/tenga26a.html}, abstract = {We introduce LinguaTriage, the first medical triage classification system for Lingala, a Bantu language of Central Africa spoken by over 45 million people with no prior supervised NLP benchmarks. Working from a 616-sample dataset of annotated symptom descriptions across three urgency levels, we develop a targeted augmentation pipeline and evaluate three architectures: fine-tuned XLM-RoBERTa (XLM-RFT), a two-stage cross-lingual transfer system (XLM-RCL), and fine-tuned AfriBERTa-Large (AfriBERTaFT). AfriBERTaFT achieves macro-F1 of 0.974 and perfect Emergency recall (1.00) on the internal test set. Mixing just 100 in-domain examples into training improves external accuracy from near-chance to 79%, demonstrating that minimal target-domain exposure far outweighs architectural choices for generalisation.} }
Endnote
%0 Conference Paper %T LinguaTriage: Cross-Lingual Transfer and African Language Pretraining for Low-Resource Medical Triage in Lingala %A Patrick S. Tenga %A Mohamed A. Kholief %B Proceedings of IndabaX Nigeria 2026: Building Scalable AI That Works: From Research to Deployment in Resource-Constrained Environments %C Proceedings of Machine Learning Research %D 2026 %E Sakinat Folorunso %E Roseline Ogundokun %E Francisca Oladipo %F pmlr-v319-tenga26a %I PMLR %P 87--100 %U https://proceedings.mlr.press/v319/tenga26a.html %V 319 %X We introduce LinguaTriage, the first medical triage classification system for Lingala, a Bantu language of Central Africa spoken by over 45 million people with no prior supervised NLP benchmarks. Working from a 616-sample dataset of annotated symptom descriptions across three urgency levels, we develop a targeted augmentation pipeline and evaluate three architectures: fine-tuned XLM-RoBERTa (XLM-RFT), a two-stage cross-lingual transfer system (XLM-RCL), and fine-tuned AfriBERTa-Large (AfriBERTaFT). AfriBERTaFT achieves macro-F1 of 0.974 and perfect Emergency recall (1.00) on the internal test set. Mixing just 100 in-domain examples into training improves external accuracy from near-chance to 79%, demonstrating that minimal target-domain exposure far outweighs architectural choices for generalisation.
APA
Tenga, P.S. & Kholief, M.A.. (2026). LinguaTriage: Cross-Lingual Transfer and African Language Pretraining for Low-Resource Medical Triage in Lingala. Proceedings of IndabaX Nigeria 2026: Building Scalable AI That Works: From Research to Deployment in Resource-Constrained Environments, in Proceedings of Machine Learning Research 319:87-100 Available from https://proceedings.mlr.press/v319/tenga26a.html.

Related Material