相关论文: MAGE: Multi-Head Attention Guided Embeddings for L…

Modern large language models become multimodal, analyzing various data formats like text and images. While fine-tuning is effective for adapting these multimodal language models (MLMs) to downstream tasks, full fine-tuning is…

Data augmentation techniques are widely used for enhancing the performance of machine learning models by tackling class imbalance issues and data sparsity. State-of-the-art generative language models have been shown to provide significant…

Despite rapid advances in large language models (LLMs), their integration with traditional supervised machine learning (ML) techniques that have proven applicability to medical data remains underexplored. This is particularly true for…

Accurate assessment of cognitive decline from spontaneous speech remains challenging due to limited dataset size and class imbalance. In this work, we propose a large language model (LLM)-driven data augmentation framework to improve the…

Although large language models (LLMs) have achieved significant success in natural language processing, they still struggle with long-context comprehension. Traditional approaches to mitigating this issue typically rely on fine-tuning or…

In recent times, word embeddings are taking a significant role in sentiment analysis. As the generation of word embeddings needs huge corpora, many applications use pretrained embeddings. In spite of the success, word embeddings suffers…

The ability of generative language models (GLMs) to generate text has improved considerably in the last few years, enabling their use for generative data augmentation. In this work, we propose CONDA, an approach to further improve GLMs'…

Large language models (LLMs) have revolutionized various domains but still struggle with non-Latin scripts and low-resource languages. This paper addresses the critical challenge of improving multilingual performance without extensive…

Efforts to leverage deep learning models in low-resource regimes have led to numerous augmentation studies. However, the direct application of methods such as mixup and cutout to text data, is limited due to their discrete characteristics.…

Automatic readability assessment (ARA) is the task of evaluating the level of ease or difficulty of text documents for a target audience. For researchers, one of the many open problems in the field is to make such models trained for the…

Training or finetuning large-scale language models (LLMs) such as GPT-3 requires substantial computation resources, motivating recent efforts to explore parameter-efficient adaptation to downstream tasks. One practical area of research is…

For many computer vision applications, such as image description and human identification, recognizing the visual attributes of humans is an essential yet challenging problem. Its challenges originate from its multi-label nature, the large…

Language Identification (LID) is a challenging task, especially when the input texts are short and noisy such as posts and statuses on social media or chat logs on gaming forums. The task has been tackled by either designing a feature set…

Effective representation learning from text has been an active area of research in the fields of NLP and text mining. Attention mechanisms have been at the forefront in order to learn contextual sentence representations. Current…

Fine-tuning is a crucial process for adapting large language models (LLMs) to diverse applications. In certain scenarios, such as multi-tenant serving, deploying multiple LLMs becomes necessary to meet complex demands. Recent studies…

We propose a training-free approach to improve sentence embeddings leveraging test-time compute by applying generative text models for data augmentation at inference time. Unlike conventional data augmentation that utilises synthetic…

Active learning effectively collects data instances for training deep learning models when the labeled dataset is limited and the annotation cost is high. Besides active learning, data augmentation is also an effective technique to enlarge…

Big data contain rich information for machine learning algorithms to utilize when learning important features during classification tasks. Human beings express their emotion using certain words, speech (tone, pitch, speed) or facial…

Multimodal embeddings are widely used in downstream tasks such as multimodal retrieval, enabling alignment of interleaved modalities in a shared representation space. While recent studies show that Multimodal Large Language Models (MLLMs)…

Data augmentation techniques have been used to alleviate the problem of scarce labeled data in various NER tasks (flat, nested, and discontinuous NER tasks). Existing augmentation techniques either manipulate the words in the original text…