Improving neural machine translation for low resource Algerian dialect by transductive transfer learning strategy

A Slim, A Melouah, U Faghihi, K Sahib - Arabian Journal for Science and …, 2022 - Springer
This study is the first work on a transductive transfer learning approach for low-resource
neural machine translation applied to the Algerian Arabic dialect. The transductive approach …

Lmsanitator: Defending prompt-tuning against task-agnostic backdoors

C Wei, W Meng, Z Zhang, M Chen, M Zhao… - arXiv preprint arXiv …, 2023 - arxiv.org
Prompt-tuning has emerged as an attractive paradigm for deploying large-scale language
models due to its strong downstream task performance and efficient multitask serving ability …

Efficient joint learning for clinical named entity recognition and relation extraction using Fourier networks: a use case in adverse drug events

A Yazdani, D Proios, H Rouhizadeh… - arXiv preprint arXiv …, 2023 - arxiv.org
Current approaches for clinical information extraction are inefficient in terms of
computational costs and memory consumption, hindering their application to process large …

Transferring Zero-shot Multilingual Chinese-Chinese Translation Model for Chinese Minority Language Translation

Z Yan, H Zan, Y Guo, H Xu - 2024 International Conference on …, 2024 - ieeexplore.ieee.org
Transfer learning is an effective method to improve the performance of low-resource
translation, but its effectiveness heavily relies on specific languages, and transferring …

NAPG: Non-autoregressive program generation for hybrid tabular-textual question answering

T Zhang, H Xu, J van Genabith, D Xiong… - … Conference on Natural …, 2023 - Springer
Hybrid tabular-textual question answering (QA) requires reasoning from heterogeneous
information, and the types of reasoning are mainly divided into numerical reasoning and …

DSISA: A New Neural Machine Translation Combining Dependency Weight and Neighbors

L Li, A Zhang, MX Luo - ACM Transactions on Asian and Low-Resource …, 2024 - dl.acm.org
Most of the previous neural machine translations (NMT) rely on parallel corpus. Integrating
explicitly prior syntactic structure information can improve the neural machine translation. In …

Attention Link: An Efficient Attention-Based Low Resource Machine Translation Architecture

Z Min - Procedia Computer Science, 2023 - Elsevier
Transformers have emerged as a pivotal tool in machine translation. Nonetheless, their
effectiveness typically hinges on extensive training with millions of bilingual parallel corpora …

Improving Chinese-Centric Low-Resource Translation Using English-Centric Pivoted Parallel Data

X Wang, L Mu, H Xu - 2023 International Conference on Asian …, 2023 - ieeexplore.ieee.org
The good performance of Neural Machine Trans-lation (NMT) normally relies on a large
amount of parallel data, while the bilingual data between languages are usually insufficient …

A Memory-Based Neural Network Model for English to Telugu Language Translation on Different Types of Sentences.

B Bataineh, B Vamsi, A Al Bataineh… - … Journal of Advanced …, 2024 - search.ebscohost.com
In India, regional languages play an important role in government-to-public, public-to-citizen
rights, weather forecasting and farming. Depending on the state the language also changes …

Rewiring the Transformer with Depth-Wise LSTMs

H Xu, Y Song, Q Liu, J van Genabith… - Proceedings of the 2024 …, 2024 - aclanthology.org
Stacking non-linear layers allows deep neural networks to model complicated functions, and
including residual connections in Transformer layers is beneficial for convergence and …