Related papers: Correcting Arabic Soft Spelling Mistakes using BiL…

Large Language Models (LLMs) perform exceedingly well in Natural Language Understanding (NLU) tasks for many languages including English. However, despite being the fifth most-spoken language globally, Grammatical Error Correction (GEC) in…

Large language models (LLMs) are highly compute- and memory-intensive, posing significant demands on high-performance GPUs. At the same time, advances in GPU technology driven by shrinking transistor sizes and lower operating voltages have…

Large language models (LLMs) for Arabic are still dominated by Modern Standard Arabic (MSA), with limited support for Saudi dialects such as Najdi and Hijazi. This underrepresentation hinders their ability to capture authentic dialectal…

Parsing the Arabic language is a difficult task given the specificities of this language and given the scarcity of digital resources (grammars and annotated corpora). In this paper, we suggest a method for Arabic parsing based on supervised…

Basic Linear Algebra Subprograms (BLAS) is a core library in scientific computing and machine learning. This paper presents FT-BLAS, a new implementation of BLAS routines that not only tolerates soft errors on the fly, but also provides…

Despite the significant improvements achieved by large language models (LLMs) in English reasoning tasks, these models continue to struggle with multilingual reasoning. Recent studies leverage a full-parameter and two-stage training…

Attention-based sequence-to-sequence models for speech recognition jointly train an acoustic model, language model (LM), and alignment mechanism using a single neural network and require only parallel audio-text pairs. Thus, the language…

Hausa texts are often characterized by writing anomalies, such as incorrect character substitutions and spacing errors, which sometimes hinder natural language processing (NLP) applications. This paper presents an approach to automatically…

Grammatical error correction, like other machine learning tasks, greatly benefits from large quantities of high quality training data, which is typically expensive to produce. While writing a program to automatically generate realistic…

We present an efficient method for adapting a monolingual Large Language Model (LLM) to another language, addressing challenges of catastrophic forgetting and tokenizer limitations. We focus this study on adapting Llama 2 to Arabic. Our…

Dialectal Arabic (DA) poses a persistent challenge for natural language processing (NLP), as most everyday communication in the Arab world occurs in dialects that diverge significantly from Modern Standard Arabic (MSA). This linguistic…

Large Language Models (LLMs) have shown remarkable capabilities, not only in generating human-like text, but also in acquiring knowledge. This highlights the need to go beyond the typical Natural Language Processing downstream benchmarks…

Handwritten Text Recognition (HTR) under limited labeled data remains a challenging problem, particularly for Arabic-script languages. Although modern sequence-based recognizers perform well in high-resource settings, their accuracy…

Arabic language is one of the most popular languages in the world. Hundreds of millions of people in many countries around the world speak Arabic as their native speaking. However, due to complexity of Arabic language, recognition of…

Large Language Models (LLMs) have demonstrated substantial potential for error correction in Automatic Speech Recognition (ASR). However, most research focuses on utterances from short-duration speech recordings, which are the predominant…

In this work, we present several deep learning models for the automatic diacritization of Arabic text. Our models are built using two main approaches, viz. Feed-Forward Neural Network (FFNN) and Recurrent Neural Network (RNN), with several…

Motivated by the need to automate medical information extraction from free-text radiological reports, we present a bi-directional long short-term memory (BiLSTM) neural network architecture for modelling radiological language. The model has…

The automated program repair field has attracted substantial interest over the years, but despite significant research efforts, creating a system that works well for complex semantic bugs such as security vulnerabilities has proven…

Often when multiple labels are obtained for a training example it is assumed that there is an element of noise that must be accounted for. It has been shown that this disagreement can be considered signal instead of noise. In this work we…

Specialized hardware accelerators have been designed and employed to maximize the performance efficiency of Spiking Neural Networks (SNNs). However, such accelerators are vulnerable to transient faults (i.e., soft errors), which occur due…