Related papers: BERT-based Multi-Task Model for Country and Provin…

This paper describes a language representation model which combines the Bidirectional Encoder Representations from Transformers (BERT) learning mechanism described in Devlin et al. (2018) with a generalization of the Universal Transformer…

Multi-Label Text Classification (MLTC) is a fundamental task in the field of Natural Language Processing (NLP) that involves the assignment of multiple labels to a given text. MLTC has gained significant importance and has been widely…

We propose a method for joint multichannel speech dereverberation with two spatial-aware tasks: direction-of-arrival (DOA) estimation and speech separation. The proposed method addresses involved tasks as a sequence to sequence mapping…

Arabic dialect identification (ADI) tools are an important part of the large-scale data collection pipelines necessary for training speech recognition models. As these pipelines require application of ADI tools to potentially out-of-domain…

We present the results and findings of the First Nuanced Arabic Dialect Identification Shared Task (NADI). This Shared Task includes two subtasks: country-level dialect identification (Subtask 1) and province-level sub-dialect…

In this paper, we propose a novel strategy for text-independent speaker identification system: Multi-Label Training (MLT). Instead of the commonly used one-to-one correspondence between the speech and the speaker label, we divide all the…

Pretraining monolingual language models have been proven to be vital for performance in Arabic Natural Language Processing (NLP) tasks. In this paper, we conduct a comprehensive study on the role of data in Arabic Pretrained Language Models…

In this work, we adhere to explore a Multi-Tasking learning (MTL) based network to perform document attribute classification such as the font type, font size, font emphasis and scanning resolution classification of a document image. To…

Automatic Speech Recognition (ASR) systems have been gaining popularity in the recent years for their widespread usage in smart phones and speakers. Building ASR systems for task-specific scenarios is subject to the availability of…

Multi-task learning is to improve the performance of the model by transferring and exploiting common knowledge among tasks. Existing MTL works mainly focus on the scenario where label sets among multiple tasks (MTs) are usually the same,…

Natural Language Processing (NLP) is today a very active field of research and innovation. Many applications need however big sets of data for supervised learning, suitably labelled for the training purpose. This includes applications for…

The ambiguities introduced by the recombination of morphemes constructing several possible inflections for a word makes the prediction of syntactic traits in Morphologically Rich Languages (MRLs) a notoriously complicated task. We propose…

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 this paper, we present an ongoing effort in lexical semantic analysis and annotation of Modern Standard Arabic (MSA) text, a semi automatic annotation tool concerned with the morphologic, syntactic, and semantic levels of description.

Traditional deep learning methods in medical imaging often focus solely on segmentation or classification, limiting their ability to leverage shared information. Multi-task learning (MTL) addresses this by combining both tasks through…

Recent state-of-the-art language models utilize a two-phase training procedure comprised of (i) unsupervised pre-training on unlabeled text, and (ii) fine-tuning for a specific supervised task. More recently, many studies have been focused…

This study introduces an integrated approach to recognizing Arabic Sign Language (ArSL) using state-of-the-art deep learning models such as MobileNetV3, ResNet50, and EfficientNet-B2. These models are further enhanced by explainable AI…

Recent studies have shown that dual encoder models trained with the sentence-level translation ranking task are effective methods for cross-lingual sentence embedding. However, our research indicates that token-level alignment is also…

Detecting Machine-Generated Text (MGT) has emerged as a significant area of study within Natural Language Processing. While language models generate text, they often leave discernible traces, which can be scrutinized using either…

Large language models (LLMs) demonstrate strong task-specific capabilities through fine-tuning, but merging multiple fine-tuned models often leads to degraded performance due to overlapping instruction-following components. Task Arithmetic…