Adamergex: Cross-lingual transfer with large language models via adaptive adapter merging

Y Zhao, W Zhang, H Wang, K Kawaguchi… - arxiv preprint arxiv …, 2024‏ - arxiv.org
As an effective alternative to the direct fine-tuning on target tasks in specific languages,
cross-lingual transfer addresses the challenges of limited training data by decoupling''task …

Transcending language boundaries: Harnessing llms for low-resource language translation

P Shu, J Chen, Z Liu, H Wang, Z Wu, T Zhong… - arxiv preprint arxiv …, 2024‏ - arxiv.org
Large Language Models (LLMs) have demonstrated remarkable success across a wide
range of tasks and domains. However, their performance in low-resource language …

Revolutionising translation with AI: Unravelling neural machine translation and generative pre-trained large language models

SC Siu - New advances in translation technology: Applications …, 2024‏ - Springer
This work explores the technical advancements in artificial intelligence (AI) for translation,
with a focus on neural machine translation (NMT) and large language models (LLMs) as …

LCS: A language converter strategy for zero-shot neural machine translation

Z Sun, Y Liu, F Meng, J Xu, Y Chen, J Zhou - arxiv preprint arxiv …, 2024‏ - arxiv.org
Multilingual neural machine translation models generally distinguish translation directions
by the language tag (LT) in front of the source or target sentences. However, current LT …

Languages transferred within the encoder: On representation transfer in zero-shot multilingual translation

Z Qu, C Ding, T Watanabe - arxiv preprint arxiv:2406.08092, 2024‏ - arxiv.org
Understanding representation transfer in multilingual neural machine translation can reveal
the representational issue causing the zero-shot translation deficiency. In this work, we …

Transformer-Based Amharic-to-English Machine Translation with Character Embedding and Combined Regularization Techniques

SH Asefa, Y Assabie - IEEE Access, 2024‏ - ieeexplore.ieee.org
Amharic is the working language of Ethiopia and, owing to its Semitic characteristics, the
language is known for its complex morphology. It is also an under-resourced language …

Improving multilingual neural machine translation by utilizing semantic and linguistic features

M Bu, S Gu, Y Feng - arxiv preprint arxiv:2408.01394, 2024‏ - arxiv.org
The many-to-many multilingual neural machine translation can be regarded as the process
of integrating semantic features from the source sentences and linguistic features from the …

How Multilingual Are Large Language Models Fine-Tuned for Translation?

A Richburg, M Carpuat - arxiv preprint arxiv:2405.20512, 2024‏ - arxiv.org
A new paradigm for machine translation has recently emerged: fine-tuning large language
models (LLM) on parallel text has been shown to outperform dedicated translation systems …

Learning multilingual sentence representations with cross-lingual consistency regularization

P Gao, L Zhang, Z He, H Wu, H Wang - arxiv preprint arxiv:2306.06919, 2023‏ - arxiv.org
Multilingual sentence representations are the foundation for similarity-based bitext mining,
which is crucial for scaling multilingual neural machine translation (NMT) system to more …

An empirical study of consistency regularization for end-to-end speech-to-text translation

P Gao, R Zhang, Z He, H Wu, H Wang - arxiv preprint arxiv:2308.14482, 2023‏ - arxiv.org
Consistency regularization methods, such as R-Drop (Liang et al., 2021) and CrossConST
(Gao et al., 2023), have achieved impressive supervised and zero-shot performance in the …