Related papers: Zero-Resource Multi-Dialectal Arabic Natural Langu…
This paper presents a novel approach to fine-tuning the Qwen2-1.5B model for Arabic language processing using Quantized Low-Rank Adaptation (QLoRA) on a system with only 4GB VRAM. We detail the process of adapting this large language model…
Expanding new functionalities efficiently is an ongoing challenge for single-turn task-oriented dialogue systems. In this work, we explore functionality-specific semi-supervised learning via self-training. We consider methods that augment…
Domain adaptation (DA) is the topical problem of adapting models from labelled source datasets so that they perform well on target datasets where only unlabelled or partially labelled data is available. Many methods have been proposed to…
Accurate detection of offensive content on social media demands high-quality labeled data; however, such data is often scarce due to the low prevalence of offensive instances and the high cost of manual annotation. To address this…
In the current era of digital communication and widespread use of social media, it is crucial to develop an understanding of persuasive techniques employed in written text. This knowledge is essential for effectively discerning accurate…
Large Language Models (LLMs) have demonstrated remarkable capabilities across numerous languages; however, their effectiveness in low-resource languages like Persian requires thorough investigation. This paper presents a comprehensive…
One of the challenges with finetuning pretrained language models (PLMs) is that their tokenizer is optimized for the language(s) it was pretrained on, but brittle when it comes to previously unseen variations in the data. This can for…
This work proposes a robust Partial Domain Adaptation (PDA) framework that mitigates the negative transfer problem by incorporating a robust target-supervision strategy. It leverages ensemble learning and includes diverse, complementary…
State-of-the-art computer vision models are mostly trained with supervised learning using human-labeled images, which limits their scalability due to the expensive annotation cost. While self-supervised representation learning has achieved…
Time-series question answering (TSQA) tasks face significant challenges due to the lack of labeled data. Alternatively, with recent advancements in large-scale models, vision-language models (VLMs) have demonstrated the potential to analyze…
Large Language Models (LLMs) are now integral to numerous industries, increasingly serving as the core reasoning engine for autonomous agents that perform complex tasks through tool-use. While the development of Arabic-native LLMs is…
In this paper, we tackle the Nuanced Arabic Dialect Identification (NADI) shared task (Abdul-Mageed et al., 2021) and demonstrate state-of-the-art results on all of its four subtasks. Tasks are to identify the geographic origin of short…
Large language models (LLMs) remain prone to factual inaccuracies and computational errors, including hallucinations and mistakes in mathematical reasoning. Recent work augmented LLMs with tools to mitigate these shortcomings, but often…
Zero-shot cross-lingual transfer utilizing multilingual LLMs has become a popular learning paradigm for low-resource languages with no labeled training data. However, for NLP tasks that involve fine-grained predictions on words and phrases,…
Source-free domain adaptation (SFDA) aims to adapt a source model trained on a fully-labeled source domain to a related but unlabeled target domain. While the source model is a key avenue for acquiring target pseudolabels, the generated…
Large language models (LLMs) often necessitate extensive labeled datasets and training compute to achieve impressive performance across downstream tasks. This paper explores a self-training paradigm, where the LLM autonomously curates its…
This paper explores a simple method for improving the zero-shot learning abilities of language models. We show that instruction tuning -- finetuning language models on a collection of tasks described via instructions -- substantially…
This paper explores zero-label learning in Natural Language Processing (NLP), whereby no human-annotated data is used anywhere during training and models are trained purely on synthetic data. At the core of our framework is a novel approach…
Automatic speech recognition (ASR) for low-resource languages remains a challenge due to the scarcity of labeled training data. Parameter-efficient fine-tuning and text-only adaptation are two popular methods that have been used to address…
We tackle the problem of zero-shot cross-lingual transfer in NLP tasks via the use of language adapters (LAs). Most of the earlier works have explored training with adapter of a single source (often English), and testing either using the…