Related papers: Self-Training Pre-Trained Language Models for Zero…

Grammar competency estimation is essential for assessing linguistic proficiency in both written and spoken language; however, the spoken modality presents additional challenges due to its spontaneous, unstructured, and disfluent nature.…

Language models (LMs) have demonstrated remarkable capabilities in NLP, yet adapting them efficiently and robustly to specific tasks remains challenging. As their scale and complexity grow, fine-tuning LMs on labelled data often…

Training a neural network model for recognizing multiple labels associated with an image, including identifying unseen labels, is challenging, especially for images that portray numerous semantically diverse labels. As challenging as this…

Despite growing interest in incorporating feedback to improve language models, most efforts focus only on sequence-level annotations. In this work, we explore the potential of utilizing fine-grained span-level annotations from offline…

Dialect and standard language identification are crucial tasks for many Arabic natural language processing applications. In this paper, we present our deep learning-based system, submitted to the second NADI shared task for country-level…

Scaling up weakly-supervised datasets has shown to be highly effective in the image-text domain and has contributed to most of the recent state-of-the-art computer vision and multimodal neural networks. However, existing large-scale…

Pre-training a recognition model with contrastive learning on a large dataset of unlabeled data has shown great potential to boost the performance of a downstream task, e.g., image classification. However, in domains such as medical…

Effort in releasing large-scale datasets may be compromised by privacy and intellectual property considerations. A feasible alternative is to release pre-trained models instead. While these models are strong on their original task (source…

While neural text-to-speech (TTS) has achieved human-like natural synthetic speech, multilingual TTS systems are limited to resource-rich languages due to the need for paired text and studio-quality audio data. This paper proposes a method…

As acquiring manual labels on data could be costly, unsupervised domain adaptation (UDA), which transfers knowledge learned from a rich-label dataset to the unlabeled target dataset, is gaining increasing popularity. While extensive studies…

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…

In this paper we present a system that exploits different pre-trained Language Models for assigning domain labels to WordNet synsets without any kind of supervision. Furthermore, the system is not restricted to use a particular set of…

While billions of non-English speaking users rely on search engines every day, the problem of ad-hoc information retrieval is rarely studied for non-English languages. This is primarily due to a lack of data set that are suitable to train…

Fine-tuning neural networks is widely used to transfer valuable knowledge from high-resource to low-resource domains. In a standard fine-tuning scheme, source and target problems are trained using the same architecture. Although capable of…

Dialectal Arabic (DA) speech data vary widely in domain coverage, dialect labeling practices, and recording conditions, complicating cross-dataset comparison and model evaluation. To characterize this landscape, we conduct a computational…

Training deep networks with noisy labels leads to poor generalization and degraded accuracy due to overfitting to label noise. Existing approaches for learning with noisy labels often rely on the availability of a clean subset of data. By…

This paper presents a comprehensive study to efficiently build named entity recognition (NER) systems when a small number of in-domain labeled data is available. Based upon recent Transformer-based self-supervised pre-trained language…

We have gained access to vast amounts of multi-omics data thanks to Next Generation Sequencing. However, it is challenging to analyse this data due to its high dimensionality and much of it not being annotated. Lack of annotated data is a…

PLDA is a popular normalization approach for the i-vector model, and it has delivered state-of-the-art performance in speaker verification. However, PLDA training requires a large amount of labeled development data, which is highly…

Recent audio LLMs have emerged rapidly, demonstrating strong generalization across various speech tasks. However, given the inherent complexity of speech signals, these models inevitably suffer from performance degradation in specific…