Related papers: AfriScience-MT: Towards Decolonizing Science in Af…

Achieving universal translation between all human language pairs is the holy-grail of machine translation (MT) research. While recent progress in massively multilingual MT is one step closer to reaching this goal, it is becoming evident…

Africa's rich linguistic diversity remains significantly underrepresented in speech technologies, creating barriers to digital inclusion. To alleviate this challenge, we systematically map the continent's speech space of datasets and…

Despite significant efforts to democratize artificial intelligence (AI), computer vision which is a sub-field of AI, still lags in Africa. A significant factor to this, is the limited access to computing resources, datasets, and…

We present the Thiomi Dataset, a large-scale multimodal corpus spanning ten African languages across four language families: Swahili, Kikuyu, Kamba, Kimeru, Luo, Maasai, Kipsigis, Somali (East Africa); Wolof (West Africa); and Fulani…

This paper reports on the semi-supervised development of acoustic and language models for under-resourced, code-switched speech in five South African languages. Two approaches are considered. The first constructs four separate bilingual…

This study investigates machine translation between related languages i.e., languages within the same family that share linguistic characteristics such as word order and lexical similarity. Machine translation through few-shot prompting…

Document-level neural machine translation (DocNMT) achieves coherent translations by incorporating cross-sentence context. However, for most language pairs there's a shortage of parallel documents, although parallel sentences are readily…

Recent advances in speech synthesis have enabled many useful applications like audio directions in Google Maps, screen readers, and automated content generation on platforms like TikTok. However, these systems are mostly dominated by voices…

Large Language Models (LLMs) have shown remarkable capabilities, not only in generating human-like text, but also in acquiring knowledge. This highlights the need to go beyond the typical Natural Language Processing downstream benchmarks…

In Africa, and the world at large, there is an increasing focus on developing Neural Machine Translation (NMT) systems to overcome language barriers. NMT for Low-resource language is particularly compelling as it involves learning with…

The linguistic diversity across the African continent presents different challenges and opportunities for machine translation. This study explores the effects of data augmentation techniques in improving translation systems in low-resource…

All over the world and especially in Africa, researchers are putting efforts into building Neural Machine Translation (NMT) systems to help tackle the language barriers in Africa, a continent of over 2000 different languages. However, the…

As large language models (LLMs) grow and develop, so do their data demands. This is especially true for multilingual LLMs, where the scarcity of high-quality and readily available data online has led to a multitude of synthetic dataset…

Scientific information expresses human understanding of nature. This knowledge is largely disseminated in different forms of text, including scientific papers, news articles, and discourse among people on social media. While important for…

We present COMET, a neural framework for training multilingual machine translation evaluation models which obtains new state-of-the-art levels of correlation with human judgements. Our framework leverages recent breakthroughs in…

Current state-of-the-art models demonstrate capacity to leverage in-context learning to translate into previously unseen language contexts. Tanzer et al. [2024] utilize language materials (e.g. a grammar) to improve translation quality for…

In many scientific fields, large language models (LLMs) have revolutionized the way text and other modalities of data (e.g., molecules and proteins) are handled, achieving superior performance in various applications and augmenting the…

Multilingual pre-trained language models (PLMs) have demonstrated impressive performance on several downstream tasks for both high-resourced and low-resourced languages. However, there is still a large performance drop for languages unseen…

Researchers working on low-resource languages face persistent challenges due to limited data availability and restricted access to computational resources. Although most large language models (LLMs) are predominantly trained in…

In recent years, Neural Machine Translation (NMT) has been shown to be more effective than phrase-based statistical methods, thus quickly becoming the state of the art in machine translation (MT). However, NMT systems are limited in…