Related papers: Using Weak Supervision and Data Augmentation in Qu…

QA models based on pretrained language mod-els have achieved remarkable performance on various benchmark datasets.However, QA models do not generalize well to unseen data that falls outside the training distribution, due to distributional…

We propose a method to perform audio event detection under the common constraint that only limited training data are available. In training a deep learning system to perform audio event detection, two practical problems arise. Firstly, most…

Deep learning models have demonstrated superior performance in various healthcare applications. However, the major limitation of these deep models is usually the lack of high-quality training data due to the private and sensitive nature of…

Intimacy is an essential element of human relationships and language is a crucial means of conveying it. Textual intimacy analysis can reveal social norms in different contexts and serve as a benchmark for testing computational models'…

The automation of text summarisation of biomedical publications is a pressing need due to the plethora of information available on-line. This paper explores the impact of several supervised machine learning approaches for extracting…

Deep learning (DL) techniques are highly effective for defect detection from images. Training DL classification models, however, requires vast amounts of labeled data which is often expensive to collect. In many cases, not only the…

Monitoring public sentiment via social media is potentially helpful during health crises such as the COVID-19 pandemic. However, traditional frequency-based, data-driven neural network-based approaches can miss newly relevant content due to…

Data augmentation is vital to the generalization ability and robustness of deep neural networks (DNNs) models. Existing augmentation methods for speaker verification manipulate the raw signal, which are time-consuming and the augmented…

Training deep neural networks requires many training samples, but in practice training labels are expensive to obtain and may be of varying quality, as some may be from trusted expert labelers while others might be from heuristics or other…

Due to the semantic complexity of the Relation extraction (RE) task, obtaining high-quality human labelled data is an expensive and noisy process. To improve the sample efficiency of the models, semi-supervised learning (SSL) methods aim to…

Question Answering (QA) effectively evaluates language models' reasoning and knowledge depth. While QA datasets are plentiful in areas like general domain and biomedicine, academic chemistry is less explored. Chemical QA plays a crucial…

The large adoption of the self-attention (i.e. transformer model) and BERT-like training principles has recently resulted in a number of high performing models on a large panoply of vision-and-language problems (such as Visual Question…

Quantifying COVID-19 infection over time is an important task to manage the hospitalization of patients during a global pandemic. Recently, deep learning-based approaches have been proposed to help radiologists automatically quantify…

Label noise is common in large real-world datasets, and its presence harms the training process of deep neural networks. Although several works have focused on the training strategies to address this problem, there are few studies that…

As an effective strategy, data augmentation (DA) alleviates data scarcity scenarios where deep learning techniques may fail. It is widely applied in computer vision then introduced to natural language processing and achieves improvements in…

Cerebral Microbleeds (CMBs), typically captured as hypointensities from susceptibility-weighted imaging (SWI), are particularly important for the study of dementia, cerebrovascular disease, and normal aging. Recent studies on COVID-19 have…

Training deep neural networks requires massive amounts of training data, but for many tasks only limited labeled data is available. This makes weak supervision attractive, using weak or noisy signals like the output of heuristic methods or…

Question Answering (QA) is key for making possible a robust communication between human and machine. Modern language models used for QA have surpassed the human-performance in several essential tasks; however, these models require large…

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.…

There is vivid research on adapting Large Language Models (LLMs) to perform a variety of tasks in high-stakes domains such as healthcare. Despite their popularity, there is a lack of understanding of the extent and contributing factors that…