Related papers: Text Normalization for Low-Resource Languages of A…

Tokenization inefficiency imposes structural disadvantages on morphologically complex, low-resource languages, inflating compute resources and depressing accuracy. We evaluate 10 large language models (LLMs) on AfriMMLU (9,000 MCQA items; 5…

Stopwords are fundamental in Natural Language Processing (NLP) techniques for information retrieval. One of the common tasks in preprocessing of text data is the removal of stopwords. Currently, while high-resource languages like English…

Reproducible benchmarks are crucial in driving progress of machine translation research. However, existing machine translation benchmarks have been mostly limited to high-resource or well-represented languages. Despite an increasing…

In recent times training Language Models (LMs) have relied on computationally heavy training over massive datasets which makes this training process extremely laborious. In this paper we propose a novel method for numerically evaluating…

Recent advances in neural TTS have led to models that can produce high-quality synthetic speech. However, these models typically require large amounts of training data, which can make it costly to produce a new voice with the desired…

This work explores fine-tuning OpenAI's Whisper automatic speech recognition (ASR) model for Amharic, a low-resource language, to improve transcription accuracy. While the foundational Whisper model struggles with Amharic due to limited…

Neural Machine Translation (NMT) for low-resource languages suffers from low performance because of the lack of large amounts of parallel data and language diversity. To contribute to ameliorating this problem, we built a baseline model for…

With the emergence of automatic speech recognition (ASR) models, converting the spoken form text (from ASR) to the written form is in urgent need. This inverse text normalization (ITN) problem attracts the attention of researchers from…

Learned metrics such as BLEURT have in recent years become widely employed to evaluate the quality of machine translation systems. Training such metrics requires data which can be expensive and difficult to acquire, particularly for…

This paper addresses the classification of Arabic text data in the field of Natural Language Processing (NLP), with a particular focus on Natural Language Inference (NLI) and Contradiction Detection (CD). Arabic is considered a…

Recent speech technologies have led to produce high quality synthesised speech due to recent advances in neural Text to Speech (TTS). However, such TTS models depend on extensive amounts of data that can be costly to produce and is hardly…

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…

Deep neural networks and huge language models are becoming omnipresent in natural language applications. As they are known for requiring large amounts of training data, there is a growing body of work to improve the performance in…

Developing Text Normalization (TN) systems for Text-to-Speech (TTS) on new languages is hard. We propose a novel architecture to facilitate it for multiple languages while using data less than 3% of the size of the data used by the state of…

Unsupervised translation has reached impressive performance on resource-rich language pairs such as English-French and English-German. However, early studies have shown that in more realistic settings involving low-resource, rare languages,…

Sentiment analysis (SA) plays a vital role in Natural Language Processing (NLP) by ~identifying sentiments expressed in text. Although significant advances have been made in SA for widely spoken languages, low-resource languages such as…

Recent studies show that large language models (LLMs) are powerful tools for working with natural language, bringing advances in many areas of computational linguistics. However, these models face challenges when applied to low-resource…

For high-resource languages like English, text classification is a well-studied task. The performance of modern NLP models easily achieves an accuracy of more than 90% in many standard datasets for text classification in English (Xie et…

Many attempts have been made in multilingual NLP to ensure that pre-trained language models, such as mBERT or GPT2 get better and become applicable to low-resource languages. To achieve multilingualism for pre-trained language models…

Low-resource African languages remain underrepresented in sentiment analysis, limiting both lexical coverage and the performance of multilingual Natural Language Processing (NLP) systems. This study proposes TriLex, a three-stage retrieval…