Related papers: Sadeed: Advancing Arabic Diacritization Through Sm…

Although many Automatic Speech Recognition (ASR) systems have been developed for Modern Standard Arabic (MSA) and Dialectal Arabic (DA), few studies have focused on dialect-specific implementations, particularly for low-resource Arabic…

Arabic is one of the most important and growing languages in the world. With the rise of social media platforms such as Twitter, Arabic spoken dialects have become more in use. In this paper, we describe our approach on the NADI Shared Task…

This survey provides the first systematic review of Arabic LLM benchmarks, analyzing 40+ evaluation benchmarks across NLP tasks, knowledge domains, cultural understanding, and specialized capabilities. We propose a taxonomy organizing…

Large Language Models (LLMs) are increasingly used to answer everyday questions, yet their performance on culturally grounded and dialectal content remains uneven across languages. We propose a comprehensive method that (i) translates…

We observe a recent behaviour on social media, in which users intentionally remove consonantal dots from Arabic letters, in order to bypass content-classification algorithms. Content classification is typically done by fine-tuning…

We present a simple, model-agnostic post-processing technique for fine-grained Arabic readability classification in the BAREC 2025 Shared Task (19 ordinal levels). Our method applies conformal prediction to generate prediction sets with…

Large Language Models (LLMs) have demonstrated remarkable capabilities in natural language processing; however, they often struggle to accurately capture and reflect cultural nuances. This research addresses this challenge by focusing on…

Urdu, spoken by 230 million people worldwide, lacks dedicated transformer-based language models and curated corpora. While multilingual models provide limited Urdu support, they suffer from poor performance, high computational costs, and…

The NLP pipeline has evolved dramatically in the last few years. The first step in the pipeline is to find suitable annotated datasets to evaluate the tasks we are trying to solve. Unfortunately, most of the published datasets lack metadata…

We present MSAs winning system for the BAREC 2025 Shared Task on fine-grained Arabic readability assessment, achieving first place in six of six tracks. Our approach is a confidence-weighted ensemble of four complementary transformer models…

Large language models (LLMs) finetuned to follow human instruction have recently exhibited significant capabilities in various English NLP tasks. However, their performance in grammatical error correction (GEC), especially on languages…

Modern Arabic ASR systems such as wav2vec 2.0 excel at word- and sentence-level transcription, yet struggle to classify isolated letters. In this study, we show that this phoneme-level task, crucial for language learning, speech therapy,…

This paper addresses the critical need for democratizing large language models (LLM) in the Arab world, a region that has seen slower progress in developing models comparable to state-of-the-art offerings like GPT-4 or ChatGPT 3.5, due to a…

Current Machine Translation (MT) systems for Arabic often struggle to account for dialectal diversity, frequently homogenizing dialectal inputs into Modern Standard Arabic (MSA) and offering limited user control over the target vernacular.…

We introduce SinaTools, an open-source Python package for Arabic natural language processing and understanding. SinaTools is a unified package allowing people to integrate it into their system workflow, offering solutions for various tasks…

The first step in any NLP pipeline is to split the text into individual tokens. The most obvious and straightforward approach is to use words as tokens. However, given a large text corpus, representing all the words is not efficient in…

Building high-quality large language models (LLMs) for enterprise Arabic applications remains challenging due to the limited availability of digitized Arabic data. In this work, we present a data synthesis and refinement strategy to help…

Semantic segmentation is a core component of discourse analysis, yet existing models are primarily developed and evaluated on high-resource written text, limiting their effectiveness on low-resource spoken varieties. In particular,…

Speech synthesis is the artificial production of human speech. A typical text-to-speech system converts a language text into a waveform. There exist many English TTS systems that produce mature, natural, and human-like speech synthesizers.…

Large language models have achieved strong performance across many NLP tasks, yet Urdu remains comparatively underexplored due to limited resources and fragmented evaluation settings. To address this gap, we introduce DunbaaBERT, a family…