Efficient Adaptation of English Language Models for Morphologically Rich and Underrepresented Languages: The Case of Arabic

Efficient Multilingual Neural Machine Translation via Corpus-Driven Vocabulary Pruning: An English-Arabic Case Study

This paper proposes a general optimization framework that combines a vocabulary pruning method with a targeted fine-tuning protocol for MNMT models, and reduces the vocabulary size from over 128,000 to approximately 10,000 tokens, enabling a 60% memory saving without any loss in performance.

A Supervised Morphosyntactic Analyzer for Modern and Classical Arabic Text

Arabic morphological analysis remains a central challenge for natural language processing (NLP). This challenge is embedded within the complex, rich, and multi-layered morphology of Arabic, where orthographic words encode enclitics, root-and-pattern derivations, and other morphosyntactic features. Another dimension of...

Arabic ChartSumm: An English-to-Arabic Benchmark for Metadata-to-Text Summarization

RAÍZ: A Hybrid Transformer-Based Machine Translation Architecture with Linguistic Preprocessing and Community Validation for Low-Resource Indigenous Languages (Spanish – Nahuatl and Spanish – Mazahua)

AraSSM: A bidirectional state-space encoder for Arabic masked language modeling

A bidirectional Mamba encoder pretrained via masked language modeling on a corpus combining Arabic Wikipedia and CulturaX text is introduced, trained end-to-end on four consumer-grade NVIDIA RTX 2080Ti GPUs (11GB) over approximately ten days.

STAR: instruction tuning for Arabic across tasks, datasets, and models

An in-depth evaluation of instruction tuning for Arabic NLP tasks using three prominent LLMs: LLaMA 3.1-8B, AceGPT-v2-8B, and Qwen3-8B shows that instruction tuning consistently improves performance across most tasks, with notable variations in effectiveness across different tasks and prompts.