2 papers
cs.CL2026
AraSSM: A bidirectional state-space encoder for Arabic masked language modeling
Ahmed Amine Aliane, Hassina Aliane, Nasredine Semmar
Pretrained Transformer encoders such as AraBERT, MARBERT, and CAMeLBERT have become the standard backbone for Arabic natural language understanding, but their self-attention mechan…
cs.CL2026
Efficient Multilingual Neural Machine Translation via Corpus-Driven Vocabulary Pruning: An English-Arabic Case Study
Ahmed Amine Aliane, Nasredine Semmar, Hassina Aliane
The adoption of large pre-trained multilingual models for neural machine translation (MNMT) faces a major challenge: excessive memory and computational consumption due to overly la…