Related papers: Low-Resource Neural Machine Translation for Southe…
Low-resource languages serve as invaluable repositories of human history, preserving cultural and intellectual diversity. Despite their significance, they remain largely absent from modern natural language processing systems. While progress…
We release the first neural machine translation system for translation between Russian, Azerbaijani and the endangered Lezgian languages, as well as monolingual and parallel datasets collected and aligned for training and evaluating the…
Machine translation systems achieve near human-level performance on some languages, yet their effectiveness strongly relies on the availability of large amounts of parallel sentences, which hinders their applicability to the majority of…
Transfer learning between different language pairs has shown its effectiveness for Neural Machine Translation (NMT) in low-resource scenario. However, existing transfer methods involving a common target language are far from success in the…
Recent advances in training multilingual language models on large datasets seem to have shown promising results in knowledge transfer across languages and achieve high performance on downstream tasks. However, we question to what extent the…
We study the selection of transfer languages for automatic abusive language detection. Instead of preparing a dataset for every language, we demonstrate the effectiveness of cross-lingual transfer learning for zero-shot abusive language…
We present effective pre-training strategies for neural machine translation (NMT) using parallel corpora involving a pivot language, i.e., source-pivot and pivot-target, leading to a significant improvement in source-target translation. We…
This paper introduces AFRIDOC-MT, a document-level multi-parallel translation dataset covering English and five African languages: Amharic, Hausa, Swahili, Yor\`ub\'a, and Zulu. The dataset comprises 334 health and 271 information…
Zero-shot translation aims to translate between language pairs not seen during training in Multilingual Machine Translation (MMT) and is largely considered an open problem. A common, albeit resource-consuming, solution is to add as many…
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,…
We address the task of machine translation (MT) from extremely low-resource language (ELRL) to English by leveraging cross-lingual transfer from 'closely-related' high-resource language (HRL). The development of an MT system for ELRL is…
The rapid advancement of Large Language Models (LLMs), particularly those trained on multilingual corpora, has intensified the need for a deeper understanding of their performance across a diverse range of languages and model sizes. Our…
Zero-resource cross-lingual transfer approaches aim to apply supervised models from a source language to unlabelled target languages. In this paper we perform an in-depth study of the two main techniques employed so far for cross-lingual…
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…
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…
As large language models (LLMs) expand multilingual capabilities, questions remain about the equity of their performance across languages. While many communities stand to benefit from AI systems, the dominance of English in training data…
Despite remarkable advances in natural language processing, developing effective systems for low-resource languages remains a formidable challenge, with performances typically lagging far behind high-resource counterparts due to data…
Neural machine translation is known to require large numbers of parallel training sentences, which generally prevent it from excelling on low-resource language pairs. This thesis explores the use of cross-lingual transfer learning on neural…
This paper presents techniques and findings for improving the performance of low-resource speech to text translation (ST). We conducted experiments on both simulated and real-low resource setups, on language pairs English - Portuguese, and…
Transformers that are pre-trained on multilingual corpora, such as, mBERT and XLM-RoBERTa, have achieved impressive cross-lingual transfer capabilities. In the zero-shot transfer setting, only English training data is used, and the…