Hausa Visual Question Answer

Hausa Visual Question Answer (in short HaVQA ), is a multimodal dataset consisting of text and images suitable for visual question answering (VQA), Visual Question Entailment (VQE), and multimodal machine translation (MMT) tasks for the Hausa language and multimodal research.  The dataset contains 1,555 unique images and 12,044 gold-standard English-Hausa parallel sentences.