Related papers: Understanding temporally weakly supervised trainin…
Name tagging in low-resource languages or domains suffers from inadequate training data. Existing work heavily relies on additional information, while leaving those noisy annotations unexplored that extensively exist on the web. In this…
Generating training sets for deep convolutional neural networks (DCNNs) is a bottleneck for modern real-world applications. This is a demanding task for applications where annotating training data is costly, such as in semantic…
Constrained optimization problems arise in various engineering systems such as inventory management and power grids. Standard deep neural network (DNN) based machine learning proxies are ineffective in practical settings where labeled data…
Keyword spotting (KWS) identifies words for voice assistants, but environmental noise frequently reduces accuracy. Standard adaptation fixes this issue and strictly requires original or labeled audio. Test time adaptation (TTA) solves this…
The performance of deep neural networks scales with dataset size and label quality, rendering the efficient mitigation of low-quality data annotations crucial for building robust and cost-effective systems. Existing strategies to address…
Existing weak supervision approaches use all the data covered by weak signals to train a classifier. We show both theoretically and empirically that this is not always optimal. Intuitively, there is a tradeoff between the amount of…
Keyword spotting (KWS) refers to the task of identifying a set of predefined words in audio streams. With the advances seen recently with deep neural networks, it has become a popular technology to activate and control small devices, such…
This study explores the robustness of label noise classifiers, aiming to enhance model resilience against noisy data in complex real-world scenarios. Label noise in supervised learning, characterized by erroneous or imprecise labels,…
The absence of labeled data for training neural models is often addressed by leveraging knowledge about the specific task, resulting in heuristic but noisy labels. The knowledge is captured in labeling functions, which detect certain…
Programmatic Weak Supervision (PWS) and generative models serve as crucial tools that enable researchers to maximize the utility of existing datasets without resorting to laborious data gathering and manual annotation processes. PWS uses…
We study the problem of learning neural text classifiers without using any labeled data, but only easy-to-provide rules as multiple weak supervision sources. This problem is challenging because rule-induced weak labels are often noisy and…
For high-resource languages like English, text classification is a well-studied task. The performance of modern NLP models easily achieves an accuracy of more than 90% in many standard datasets for text classification in English (Xie et…
Large-scale datasets have driven the rapid development of deep neural networks for visual recognition. However, annotating a massive dataset is expensive and time-consuming. Web images and their labels are, in comparison, much easier to…
In many applications, finding adequate labeled data to train predictive models is a major challenge. In this work, we propose methods to use group-level binary labels as weak supervision to train instance-level binary classification models.…
Distant supervision provides a means to create a large number of weakly labeled data at low cost for relation classification. However, the resulting labeled instances are very noisy, containing data with wrong labels. Many approaches have…
Deep neural networks are gaining increasing popularity for the classic text classification task, due to their strong expressive power and less requirement for feature engineering. Despite such attractiveness, neural text classification…
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…
This paper introduces neural architecture search (NAS) for the automatic discovery of small models for keyword spotting (KWS) in limited resource environments. We employ a differentiable NAS approach to optimize the structure of…
Neural networks have achieved remarkable success in time series classification, but their reliance on large amounts of labeled data for training limits their applicability in cold-start scenarios. Moreover, they lack interpretability,…
Supervised learning usually requires a large amount of labelled data. However, attaining ground-truth labels is costly for many tasks. Alternatively, weakly supervised methods learn with cheap weak signals that only approximately label some…