Related papers: TriLex: A Framework for Multilingual Sentiment Ana…

With the rapid development of evaluation datasets to assess LLMs understanding across a wide range of subjects and domains, identifying a suitable language understanding benchmark has become increasingly challenging. In this work, we…

Multilingual Pretrained Language Models (MPLMs) have shown their strong multilinguality in recent empirical cross-lingual transfer studies. In this paper, we propose the Prompts Augmented by Retrieval Crosslingually (PARC) pipeline to…

Automatic Speech Recognition (ASR) performance for low-resource languages is still far behind that of higher-resource languages such as English, due to a lack of sufficient labeled data. State-of-the-art methods deploy self-supervised…

Most languages of the world pose low-resource challenges to natural language processing models. With multilingual training, knowledge can be shared among languages. However, not all languages positively influence each other and it is an…

In recent years, aspect-based sentiment analysis (ABSA) has made rapid progress and shown strong practical value. However, existing research and benchmarks are largely concentrated on high-resource languages, leaving fine-grained sentiment…

Evaluating machine translation (MT) quality for under-resourced African languages remains a significant challenge, as existing metrics often suffer from limited language coverage and poor performance in low-resource settings. While recent…

Building effective tokenizers for multilingual Large Language Models (LLMs) requires careful control over language-specific data mixtures. While a tokenizer's compression performance critically affects the efficiency of LLM training and…

This paper describes our Triple X speech recognition system submitted to Task 1 of the Multi-Lingual Conversational Speech Language Modeling (MLC-SLM) Challenge. Our work focuses on optimizing speech recognition accuracy in multilingual…

We propose a hybrid approach for multilingual sentiment analysis that combines extractive and abstractive summarization to address the limitations of standalone methods. The model integrates TF-IDF-based extraction with a fine-tuned XLM-R…

High-resource language models often fall short in the African context, where there is a critical need for models that are efficient, accessible, and locally relevant, even amidst significant computing and data constraints. This paper…

RALMs (Retrieval-Augmented Language Models) broaden their knowledge scope by incorporating external textual resources. However, the multilingual nature of global knowledge necessitates RALMs to handle diverse languages, a topic that has…

Large Language Models (LLMs) are transforming Natural Language Processing (NLP), but their benefits are largely absent for Africa's 2,000 low-resource languages. This paper comparatively analyzes African language coverage across six LLMs,…

The development of Natural Language Processing (NLP) tools for low-resource languages is critically hindered by the scarcity of annotated datasets. This paper addresses this fundamental challenge by introducing HausaMovieReview, a novel…

Many natural language processing (NLP) tasks make use of massively pre-trained language models, which are computationally expensive. However, access to high computational resources added to the issue of data scarcity of African languages…

The rapid advancement of social media enables us to analyze user opinions. In recent times, sentiment analysis has shown a prominent research gap in understanding human sentiment based on the content shared on social media. Although…

Extractive Reading Comprehension (ERC) has made tremendous advances enabled by the availability of large-scale high-quality ERC training data. Despite of such rapid progress and widespread application, the datasets in languages other than…

In this paper, we improve on existing language resources for the low-resource Filipino language in two ways. First, we outline the construction of the TLUnified dataset, a large-scale pretraining corpus that serves as an improvement over…

The performance of NLP methods for severely under-resourced languages cannot currently hope to match the state of the art in NLP methods for well resourced languages. We explore the extent to which pretrained large language models (LLMs)…

Almost none of the 2,000+ languages spoken in Africa have widely available automatic speech recognition systems, and the required data is also only available for a few languages. We have experimented with two techniques which may provide…

Large Language Models (LLMs) and Large Vision-Language Models (LVLMs) demonstrate strong reasoning capabilities, yet their performance in English significantly outperforms that in low-resource languages, raising fairness concerns in…