Related papers: DiaLex: A Benchmark for Evaluating Multidialectal …

Foundation models have established unified representations for natural language processing, yet this paradigm remains largely unexplored for tabular data. Existing methods face fundamental limitations: LLM-based approaches lack…

Arabic Rhetoric is the field of Arabic linguistics which governs the art and science of conveying a message with greater beauty, impact and persuasiveness. The field is as ancient as the Arabic language itself and is found extensively in…

Text embeddings are commonly evaluated on a small set of datasets from a single task not covering their possible applications to other tasks. It is unclear whether state-of-the-art embeddings on semantic textual similarity (STS) can be…

This work is part of a large research project entitled "Or\'eodule" aimed at developing tools for automatic speech recognition, translation, and synthesis for Arabic language. Our attention has mainly been focused on an attempt to improve…

Since their inception, transformer-based language models have led to impressive performance gains across multiple natural language processing tasks. For Arabic, the current state-of-the-art results on most datasets are achieved by the…

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,…

Vowels in Arabic are optional orthographic symbols written as diacritics above or below letters. In Arabic texts, typically more than 97 percent of written words do not explicitly show any of the vowels they contain; that is to say,…

Due to an information explosion on the internet, there is a need for the development of aggregated search systems that can boost the retrieval and management of content in various formats. To further improve the clustering of Arabic text…

Arabic is a Semitic language which is widely spoken with many dialects. Given the success of pre-trained language models, many transformer models trained on Arabic and its dialects have surfaced. While there have been an extrinsic…

In recent years, machine learning has been widely adopted to automate the audio mixing process. Automatic mixing systems have been applied to various audio effects such as gain-adjustment, equalization, and reverberation. These systems can…

Studies of morphological processing have shown that semantic transparency is crucial for word recognition. Its computational operationalization is still under discussion. Our primary objectives are to explore embedding-based measures of…

Designing a natural voice interface rely mostly on Speech recognition for interaction between human and their modern digital life equipment. In addition, speech recognition narrows the gap between monolingual individuals to better exchange…

Word embeddings are an essential instrument in many NLP tasks. Most available resources are trained on general language from Web corpora or Wikipedia dumps. However, word embeddings for domain-specific language are rare, in particular for…

Pre-trained Language Models (PLMs) are integral to many modern natural language processing (NLP) systems. Although multilingual models cover a wide range of languages, they often grapple with challenges like high inference costs and a lack…

In many languages like Arabic, diacritics are used to specify pronunciations as well as meanings. Such diacritics are often omitted in written text, increasing the number of possible pronunciations and meanings for a word. This results in a…

In recent years, the enhanced capabilities of ASR models and the emergence of multi-dialect datasets have increasingly pushed Arabic ASR model development toward an all-dialect-in-one direction. This trend highlights the need for…

Most of previous work on learning diacritization of the Arabic language relied on training models from scratch. In this paper, we investigate how to leverage pre-trained language models to learn diacritization. We finetune token-free…

Arabic text recognition is a challenging task because of the cursive nature of Arabic writing system, its joint writing scheme, the large number of ligatures and many other challenges. Deep Learning DL models achieved significant progress…

Word segmentation plays a pivotal role in improving any Arabic NLP application. Therefore, a lot of research has been spent in improving its accuracy. Off-the-shelf tools, however, are: i) complicated to use and ii) domain/dialect…

Word embeddings -- distributed representations of words -- in deep learning are beneficial for many tasks in natural language processing (NLP). However, different embedding sets vary greatly in quality and characteristics of the captured…