Current benchmarks for sign language recognition (SLR) focus mainly on isolated SLR, while there are limited datasets for continuous SLR (CSLR), which recognizes sequences of signs in a video. Additionally, existing CSLR datasets are collected in controlled settings, which restricts their effectiveness in building robust real-world CSLR systems. To address these limitations, we present Isharah, a large multi-scene dataset for CSLR. It is the first dataset of its type and size, collected in an unconstrained environment using signers' smartphones. This setup resulted in high variations of recording settings, camera distances, angles, and resolutions. This variation helps with developing sign language understanding models capable of handling the variability and complexity of real-world scenarios. The dataset consists of 30,000 video clips performed by 18 deaf and professional signers. Additionally, the dataset is linguistically rich as it provides a gloss-level annotation for all dataset's videos, making it useful for developing CSLR and sign language translation (SLT) systems. This paper also introduces multiple sign language understanding benchmarks, including signer-independent and unseen-sentence CSLR, along with gloss-based and gloss-free SLT.

This study introduces a character-level approach specifically designed for Arabic NLP tasks, offering a novel and highly effective solution to the unique challenges inherent in Arabic language processing. It presents a thorough comparative study of various character-level models, including Convolutional Neural Networks (CNNs), pre-trained transformers (CANINE), and Bidirectional Long Short-Term Memory networks (BiLSTMs), assessing their performance and exploring the impact of different data augmentation techniques on enhancing their effectiveness. Additionally, it introduces two innovative Arabic-specific data augmentation methods—vowel deletion and style transfer—and rigorously evaluates their effectiveness. The proposed approach was evaluated on Arabic privacy policy classification task as a case study, demonstrating significant improvements in model performance, reporting a micro-averaged F1-score of 93.8%, surpassing state-of-the-art models.

This paper introduces essential resources for Qur’anic studies: an annotated Tafsir ontology, a dataset of approximately 4,200 question-answer pairs, and a collection of 15 structured Tafsir books available in two formats. We present a comprehensive framework for handling sensitive Qur’anic Tafsir data that spans the entire pipeline from dataset construction through evaluation and error analysis. Our work establishes new benchmarks for retrieval and question-answering tasks on Qur’anic content, comparing performance across state-of-the-art embedding models and large language models (LLMs).We introduce OntologyRAG-Q, a novel retrieval-augmented generation approach featuring our custom Ayat-Ontology chunking method that segments Tafsir content at the verse level using ontology-driven structure. Benchmarking reveals strong performance across various LLMs, with GPT-4 achieving the highest results, followed closely by ALLaM. Expert evaluations show our system achieves 69.52% accuracy and 74.36% correctness overall, though multi-hop and context-dependent questions remain challenging. Our analysis demonstrates that answer position within documents significantly impacts retrieval performance, and among the evaluation metrics tested, BERT-recall and BERT-F1 correlate most strongly with expert assessments. The resources developed in this study are publicly available at https://github.com/sazani/OntologyRAG-Q.git.

The widespread interest in large language models (LLMs) is rooted in their remarkable capacity to generate human-like and contextually relevant responses. However, the precision of LLMs within specific domains or intricate tasks, such as Arabic dialect identification, remains largely unexplored. This task presents a substantial challenge in Arabic natural language processing, given its language-dependent nature. This paper provides a framework for evaluating LLMs for Arabic dialect identification and conducts a comprehensive evaluation of LLMs, employing both tuning-free and fine-tuning-based learning paradigms. The evaluation encompasses GPT-3.5, chatGPT, GPT-4, and Google BARD for Arabic dialect identification under the tuning-free learning paradigm. Furthermore, it assesses the performance of GPT-3.5 along with AraBERT and MARBERT using the fine-tuning learning paradigm. In the tuning-free approach, GPT-4 achieves the most favorable results, reporting an F1MACof 45.60%. Under the fine-tuning learning paradigm, both AraBERT and MARBERT exhibit comparable performance (around 50% F 1MAC) to GPT-3.5, without incurring any financial costs, in contrast to the expenses associated with GPT-3.5.