21 citations · 49 across the 5 of their papers we have counts for
5 papers
Biased Embeddings from Wild Data: Measuring, Understanding and Removing
Adam Sutton, Thomas Lansdall-Welfare, Nello Cristianini
Many modern Artificial Intelligence (AI) systems make use of data embeddings, particularly in the domain of Natural Language Processing (NLP). These embeddings are learnt from data…
Right for the Right Reason: Training Agnostic Networks
Sen Jia, Thomas Lansdall-Welfare, Nello Cristianini
We consider the problem of a neural network being requested to classify images (or other inputs) without making implicit use of a "protected concept", that is a concept that should…
History Playground: A Tool for Discovering Temporal Trends in Massive Textual Corpora
Thomas Lansdall-Welfare, Nello Cristianini
Recent studies have shown that macroscopic patterns of continuity and change over the course of centuries can be detected through the analysis of time series extracted from massive…
The Anatomy of a Modular System for Media Content Analysis
Ilias Flaounas, Thomas Lansdall-Welfare, Panagiota Antonakaki +1
Intelligent systems for the annotation of media content are increasingly being used for the automation of parts of social science research. In this domain the problem of integratin…
Analysing Mood Patterns in the United Kingdom through Twitter Content
Vasileios Lampos, Thomas Lansdall-Welfare, Ricardo Araya +1
Social Media offer a vast amount of geo-located and time-stamped textual content directly generated by people. This information can be analysed to obtain insights about the general…