publications

2026

1. AfricaNLP

   AfriCaption: Establishing a New Paradigm for Image Captioning in African Languages

   Mardiyyah Oduwole , Prince Mireku , Fatimo Adebanjo , and 3 more authors

   In Proceedings of the 7th Workshop on African Natural Language Processing (AfricaNLP), co-located with EACL 2026 , 2026

   Abs arXiv Bib

   Multimodal AI research has overwhelmingly focused on high-resource languages, hindering the democratization of advancements in the field. To address this, we present AfriCaption, a comprehensive framework for multilingual image captioning in 20 African languages and our contributions are threefold: (i) a curated dataset built on Flickr8k, featuring semantically aligned captions generated via a context-aware selection and translation process; (ii) a dynamic, context-preserving pipeline that ensures ongoing quality through model ensembling and adaptive substitution; and (iii) the AfriCaption model, a 0.5B parameter vision-to-text architecture that integrates SigLIP and NLLB200 for caption generation across under-represented languages. This unified framework ensures ongoing data quality and establishes the first scalable image-captioning resource for under-represented African languages, laying the groundwork for truly inclusive multimodal AI.

   @inproceedings{oduwole2026africaption,
     title = {AfriCaption: Establishing a New Paradigm for Image Captioning in African Languages},
     author = {Oduwole, Mardiyyah and Mireku, Prince and Adebanjo, Fatimo and Olajide, Oluwatosin and Aliyu, Mahi Aminu and Novikova, Jekaterina},
     booktitle = {Proceedings of the 7th Workshop on African Natural Language Processing (AfricaNLP), co-located with EACL 2026},
     year = {2026},
   }

2025

1. arXiv

   When Distributions Shift: Causal Generalization for Low-Resource Languages

   Mahi Aminu Aliyu , Chisom Chibuike , Fatimo Adebanjo , and 2 more authors

   arXiv preprint arXiv:2510.27512, 2025

   Abs arXiv Bib

   Machine learning models often fail under distribution shifts, a problem exacerbated in low-resource settings where limited data restricts robust generalization. Domain generalization (DG) methods address this challenge by learning representations that remain invariant across domains, frequently leveraging causal principles. In this work, we study two causal DG approaches for low-resource natural language processing. First, we apply causal data augmentation using GPT-4o-mini to generate counterfactual paraphrases for sentiment classification on the NaijaSenti Twitter corpus in Yoruba and Igbo. Second, we investigate invariant causal representation learning with the Debiasing in Aspect Review (DINER) framework for aspect-based sentiment analysis. We extend DINER to a multilingual setting by introducing Afri-SemEval, a dataset of 17 languages translated from SemEval-2014 Task. Experiments show improved robustness to unseen domains, with consistent gains from counterfactual augmentation and enhanced out-of-distribution performance from causal representation learning across multiple languages.

   @article{aliyu2025causal,
     title = {When Distributions Shift: Causal Generalization for Low-Resource Languages},
     author = {Aliyu, Mahi Aminu and Chibuike, Chisom and Adebanjo, Fatimo and Awosanya, Omokolade and Oyeneye, Samuel},
     journal = {arXiv preprint arXiv:2510.27512},
     year = {2025},
   }