Related papers: Harnessing Transfer Learning from Swahili: Advanci…

Conventional spoken language translation (SLT) systems are pipeline based systems, where we have an Automatic Speech Recognition (ASR) system to convert the modality of source from speech to text and a Machine Translation (MT) systems to…

Creoles represent an under-explored and marginalized group of languages, with few available resources for NLP research.While the genealogical ties between Creoles and a number of highly-resourced languages imply a significant potential for…

This paper describes our system developed for the SemEval-2023 Task 12 "Sentiment Analysis for Low-resource African Languages using Twitter Dataset". Sentiment analysis is one of the most widely studied applications in natural language…

We investigate how large language models perform on low-resource languages by benchmarking eight LLMs across five experimental conditions in English, Kazakh, and Mongolian. Using 50 hand-crafted questions spanning factual, reasoning,…

Speech technology remains out of reach for most of the over 2300 languages in Africa. We present the first systematic assessment of large-scale synthetic voice corpora for African ASR. We apply a three-step process: LLM-driven text…

S\'ami, an indigenous language group comprising multiple languages, faces digital marginalization due to the limited availability of data and sophisticated language models designed for its linguistic intricacies. This work focuses on…

Structured prediction tasks, like machine translation, involve learning functions that map structured inputs to structured outputs. Recurrent Neural Networks (RNNs) have historically been a popular choice for such tasks, including in…

In this work, we present AfriNLLB, a series of lightweight models for efficient translation from and into African languages. AfriNLLB supports 15 language pairs (30 translation directions), including Swahili, Hausa, Yoruba, Amharic, Somali,…

South Africa and the Democratic Republic of Congo (DRC) present a complex linguistic landscape with languages such as Zulu, Sepedi, Afrikaans, French, English, and Tshiluba (Ciluba), which creates unique challenges for AI-driven translation…

Large Language Models (LLMs) have demonstrated strong translation abilities through prompting, even without task-specific training. However, their effectiveness in dialectal and low-resource contexts remains underexplored. This study…

Most Transformer language models are primarily pretrained on English text, limiting their use for other languages. As the model sizes grow, the performance gap between English and other languages with fewer compute and data resources…

Semantic role labeling is a crucial task in natural language processing, enabling better comprehension of natural language. However, the lack of annotated data in multiple languages has posed a challenge for researchers. To address this, a…

There are more than 2000 living languages in Africa, most of which have been bypassed by advances in language technology. Current leading LLMs exhibit strong performance on a number of the most common languages (e.g. Swahili or Yoruba), but…

The advent of deep learning has led to a significant gain in machine translation. However, most of the studies required a large parallel dataset which is scarce and expensive to construct and even unavailable for some languages. This paper…

Despite recent advancements in speech processing, zero-resource speech translation (ST) and automatic speech recognition (ASR) remain challenging problems. In this work, we propose to leverage a multilingual Large Language Model (LLM) to…

The disparity in language resources poses a challenge in multilingual NLP, with high-resource languages benefiting from extensive data, while low-resource languages lack sufficient data for effective training. Our Contrastive Language…

Although researchers and practitioners are pushing the boundaries and enhancing the capacities of NLP tools and methods, works on African languages are lagging. A lot of focus on well resourced languages such as English, Japanese, German,…

Low-resource languages such as isiZulu and isiXhosa face persistent challenges in machine translation due to limited parallel data and linguistic resources. Recent advances in large language models suggest that self-reflection, prompting a…

Multilingual language models have pushed state-of-the-art in cross-lingual NLP transfer. The majority of zero-shot cross-lingual transfer, however, use one and the same massively multilingual transformer (e.g., mBERT or XLM-R) to transfer…

The goal of this work is to design a machine translation (MT) system for a low-resource family of dialects, collectively known as Swiss German, which are widely spoken in Switzerland but seldom written. We collected a significant number of…