Related papers: Paying down metadata debt: learning the representa…

Topic modelling is a popular unsupervised method for identifying the underlying themes in document collections that has many applications in information retrieval. A topic is usually represented by a list of terms ranked by their…

Recently, the usefulness of self-supervised representation learning (SSRL) methods has been confirmed in various downstream tasks. Many of these models, as exemplified by HuBERT and WavLM, use pseudo-labels generated from spectral features…

Topic models are widely used to analyze document collections. While they are valuable for discovering latent topics in a corpus when analysts are unfamiliar with the corpus, analysts also commonly start with an understanding of the content…

We investigate model based classification with partially labelled training data. In many biostatistical applications, labels are manually assigned by experts, who may leave some observations unlabelled due to class uncertainty. We analyse…

Traditional neural topic models are typically optimized by reconstructing the document's Bag-of-Words (BoW) representations, overlooking contextual information and struggling with data sparsity. In this work, we propose a novel approach to…

Representation learning with small labeled data have emerged in many problems, since the success of deep neural networks often relies on the availability of a huge amount of labeled data that is expensive to collect. To address it, many…

Topic models are widely used unsupervised models capable of learning topics - weighted lists of words and documents - from large collections of text documents. When topic models are used for discovery of topics in text collections, a…

Partial label learning deals with the problem where each training instance is assigned a set of candidate labels, only one of which is correct. This paper provides the first attempt to leverage the idea of self-training for dealing with…

Modelling Consumer Indebtedness has proven to be a problem of complex nature. In this work we utilise Data Mining techniques and methods to explore the multifaceted aspect of Consumer Indebtedness by examining the contribution of…

The growing need to analyze large collections of documents has led to great developments in topic modeling. Since documents are frequently associated with other related variables, such as labels or ratings, much interest has been placed on…

In this thesis, we study the problem of feature learning on heterogeneous knowledge graphs. These features can be used to perform tasks such as link prediction, classification and clustering on graphs. Knowledge graphs provide rich…

Learning from Multivariate Time Series (MTS) has attracted widespread attention in recent years. In particular, label shortage is a real challenge for the classification task on MTS, considering its complex dimensional and sequential data…

A key assumption in multi-task learning is that at the inference time the multi-task model only has access to a given data point but not to the data point's labels from other tasks. This presents an opportunity to extend multi-task learning…

Self-admitted technical debt (SATD) refers to a form of technical debt in which developers explicitly acknowledge and document the existence of technical shortcuts, workarounds, or temporary solutions within the codebase. Over recent years,…

Deep supervised models have an unprecedented capacity to absorb large quantities of training data. Hence, training on many datasets becomes a method of choice towards graceful degradation in unusual scenes. Unfortunately, different datasets…

Semi-supervised learning is a challenging problem which aims to construct a model by learning from limited labeled examples. Numerous methods for this task focus on utilizing the predictions of unlabeled instances consistency alone to…

Topic models are widely used in natural language processing, allowing researchers to estimate the underlying themes in a collection of documents. Most topic models use unsupervised methods and hence require the additional step of attaching…

Semi-supervised learning is a setting in which one has labeled and unlabeled data available. In this survey we explore different types of theoretical results when one uses unlabeled data in classification and regression tasks. Most methods…

A central goal of unsupervised learning is to acquire representations from unlabeled data or experience that can be used for more effective learning of downstream tasks from modest amounts of labeled data. Many prior unsupervised learning…

Meta-learning has emerged as a prominent technology for few-shot text classification and has achieved promising performance. However, existing methods often encounter difficulties in drawing accurate class prototypes from support set…