Democratizing LLMs for low-resource languages by leveraging their english dominant abilities with linguistically-diverse prompts

XP Nguyen, SM Aljunied, S Joty, L Bing - arXiv preprint arXiv:2306.11372, 2023 - arxiv.org
Large language models (LLMs) are known to effectively perform tasks by simply observing
few exemplars. However, in low-resource languages, obtaining such hand-picked …

Survey on publicly available sinhala natural language processing tools and research

N De Silva - arXiv preprint arXiv:1906.02358, 2019 - arxiv.org
Sinhala is the native language of the Sinhalese people who make up the largest ethnic
group of Sri Lanka. The language belongs to the globe-spanning language tree, Indo …

Refining low-resource unsupervised translation by language disentanglement of multilingual translation model

XP Nguyen, S Joty, K Wu… - Advances in Neural …, 2022 - proceedings.neurips.cc
Numerous recent work on unsupervised machine translation (UMT) implies that competent
unsupervised translations of low-resource and unrelated languages, such as Nepali or …

Speech-to-speech Low-resource Translation

HC Liu, MY Day, CC Wang - 2023 IEEE 24th International …, 2023 - ieeexplore.ieee.org
Speech-to-speech translation (S2ST), particularly in the context of low-resource languages,
plays a vital role in facilitating global communication. However, comprehensive research in …

Improving speech-to-speech translation through unlabeled text

XP Nguyen, S Popuri, C Wang, Y Tang… - ICASSP 2023-2023 …, 2023 - ieeexplore.ieee.org
Direct speech-to-speech translation (S2ST) is among the most challenging problems in the
translation paradigm due to the significant scarcity of S2ST data. While effort has been made …

Improving neural machine translation: data centric approaches

XP Nguyen - 2023 - dr.ntu.edu.sg
Neural machine translation (NMT), where neural networks are used to generate translations,
has revolutionized the field of machine translation (MT) in the past ten years, thanks to the …