Related papers: A Severity-Based Curriculum Learning Strategy for …

Identifying high-quality and easily accessible annotated samples poses a notable challenge in medical image analysis. Transfer learning techniques, leveraging pre-training data, offer a flexible solution to this issue. However, the impact…

We describe our team's contribution to the STRICT-SMALL track of the BabyLM Challenge. The challenge requires training a language model from scratch using only a relatively small training dataset of ten million words. We experiment with…

Learning skills by imitation is a promising concept for the intuitive teaching of robots. A common way to learn such skills is to learn a parametric model by maximizing the likelihood given the demonstrations. Yet, human demonstrations are…

As an emerging topic in face recognition, designing margin-based loss functions can increase the feature margin between different classes for enhanced discriminability. More recently, the idea of mining-based strategies is adopted to…

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…

We address the problem of scarcity of educational Arabic Language Learning tools that advocate modern pedagogical models such as active learning which ensures language proficiency. In fact, we investigate the design and evaluation of an…

Mental health disorders significantly impact people globally, regardless of background, education, or socioeconomic status. However, access to adequate care remains a challenge, particularly for underserved communities with limited…

Neural networks trained by empirical risk minimization often suffer from overfitting, especially to specific samples or domains, which leads to poor generalization. Curriculum Learning (CL) addresses this issue by selecting training samples…

Continual learning is essential for medical image classification systems to adapt to dynamically evolving clinical environments. The integration of multimodal information can significantly enhance continual learning of image classes.…

It is common knowledge that the quantity and quality of the training data play a significant role in the creation of a good machine learning model. In this paper, we take it one step further and demonstrate that the way the training…

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…

Existing curriculum learning approaches to Neural Machine Translation (NMT) require sampling sufficient amounts of "easy" samples from training data at the early training stage. This is not always achievable for low-resource languages where…

Extraction of concepts and entities of interest from non-formal texts such as social media posts and informal communication is an important capability for decision support systems in many domains, including healthcare, customer relationship…

Medical events of interest, such as mortality, often happen at a low rate in electronic medical records, as most admitted patients survive. Training models with this imbalance rate (class density discrepancy) may lead to suboptimal…

The advancement of large language models (LLMs) has opened new frontiers in natural language processing, particularly in specialized domains like healthcare. In this paper, we propose the Incremental Curriculum-Based Fine-Tuning (ICFT)…

Curriculum learning techniques are a viable solution for improving the accuracy of automatic models, by replacing the traditional random training with an easy-to-hard strategy. However, the standard curriculum methodology does not…

This work presents a novel framework for training Arabic nested embedding models through Matryoshka Embedding Learning, leveraging multilingual, Arabic-specific, and English-based models, to highlight the power of nested embeddings models…

We present Hala, a family of Arabic-centric instruction and translation models built with our translate-and-tune pipeline. We first compress a strong AR$\leftrightarrow$EN teacher to FP8 (yielding $\sim$2$\times$ higher throughput with no…

Language models (LMs) have introduced a major paradigm shift in Natural Language Processing (NLP) modeling where large pre-trained LMs became integral to most of the NLP tasks. The LMs are intelligent enough to find useful and relevant…

Sentiment analysis (SA) has been, and is still, a thriving research area. However, the task of Arabic sentiment analysis (ASA) is still underrepresented in the body of research. This study offers the first in-depth and in-breadth analysis…