Related papers: Learning Supervised Topic Models for Classificatio…

The task of text and sentence classification is associated with the need for large amounts of labelled training data. The acquisition of high volumes of labelled datasets can be expensive or unfeasible, especially for highly-specialised…

Over the last few years, deep learning has revolutionized the field of machine learning by dramatically improving the state-of-the-art in various domains. However, as the size of supervised artificial neural networks grows, typically so…

In the Humanities and Social Sciences, there is increasing interest in approaches to information extraction, prediction, intelligent linkage, and dimension reduction applicable to large text corpora. With approaches in these fields being…

Human annotations are vital to supervised learning, yet annotators often disagree on the correct label, especially as annotation tasks increase in complexity. A strategy to improve label quality is to ask multiple annotators to label the…

Noisy annotations such as missing annotations and location shifts often exist in crowd counting datasets due to multi-scale head sizes, high occlusion, etc. These noisy annotations severely affect the model training, especially for density…

Topic modelling is a text mining technique for identifying salient themes from a number of documents. The output is commonly a set of topics consisting of isolated tokens that often co-occur in such documents. Manual effort is often…

Recently, there has been a burst in the number of research projects on human computation via crowdsourcing. Multiple choice (or labeling) questions could be referred to as a common type of problem which is solved by this approach. As an…

Sequence labeling is a fundamental framework for various natural language processing problems. Its performance is largely influenced by the annotation quality and quantity in supervised learning scenarios, and obtaining ground truth labels…

We introduce supervised latent Dirichlet allocation (sLDA), a statistical model of labelled documents. The model accommodates a variety of response types. We derive an approximate maximum-likelihood procedure for parameter estimation, which…

Machine learning models for text classification are trained to predict a class for a given text. To do this, training and validation samples must be prepared: a set of texts is collected, and each text is assigned a class. These classes are…

Supervisory signals can help topic models discover low-dimensional data representations that are more interpretable for clinical tasks. We propose a framework for training supervised latent Dirichlet allocation that balances two goals:…

Automatic Crowd behavior analysis can be applied to effectively help the daily transportation statistics and planning, which helps the smart city construction. As one of the most important keys, crowd counting has drawn increasing…

Language models have been shown to reproduce underlying biases existing in their training data, which is the majority perspective by default. Proposed solutions aim to capture minority perspectives by either modelling annotator…

As a means of human-based computation, crowdsourcing has been widely used to annotate large-scale unlabeled datasets. One of the obvious challenges is how to aggregate these possibly noisy labels provided by a set of heterogeneous…

Social media communications are becoming increasingly prevalent; some useful, some false, whether unwittingly or maliciously. An increasing number of rumours daily flood the social networks. Determining their veracity in an autonomous way…

Topic models are a popular tool for understanding text collections, but their evaluation has been a point of contention. Automated evaluation metrics such as coherence are often used, however, their validity has been questioned for neural…

One of the primary catalysts fueling advances in artificial intelligence (AI) and machine learning (ML) is the availability of massive, curated datasets. A commonly used technique to curate such massive datasets is crowdsourcing, where data…

In many domains, collecting sufficient labeled training data for supervised machine learning requires easily accessible but noisy sources, such as crowdsourcing services or tagged Web data. Noisy labels occur frequently in data sets…

Argument mining is a core technology for automating argument search in large document collections. Despite its usefulness for this task, most current approaches to argument mining are designed for use only with specific text types and fall…

Pre-trained vision-language models learn massive data to model unified representations of images and natural languages, which can be widely applied to downstream machine learning tasks. In addition to zero-shot inference, in order to better…