no code implementations • RANLP 2021 • Husamelddin Balla, Marisa Llorens Salvador, Sarah Jane Delany
In this paper, we propose an interactive learning approach to tackle a target-based sentiment analysis task for the Arabic language.
no code implementations • 11 Jun 2021 • Padraig Cunningham, Bahavathy Kathirgamanathan, Sarah Jane Delany
In Machine Learning, feature selection entails selecting a subset of the available features in a dataset to use for model development.
no code implementations • 22 Feb 2021 • Xuehao Liu, Sarah Jane Delany, Susan Mckeever
We further demonstrate that by using hierarchical relationships from our external knowledge base, we can locate new unseen classes outside the CNN training set in our embeddings space, based on visual feature activations.
no code implementations • 18 May 2020 • Padraig Cunningham, Sarah Jane Delany
Often, what is termed algorithmic bias in machine learning will be due to historic bias in the training data.
1 code implementation • 9 Apr 2020 • Padraig Cunningham, Sarah Jane Delany
This paper presents an overview of techniques for Nearest Neighbour classification focusing on; mechanisms for assessing similarity (distance), computational issues in identifying nearest neighbours and mechanisms for reducing the dimension of the data.
1 code implementation • Evolving Systems 2011 • Patrick Lindstrom, Brian Mac Namee, Sarah Jane Delany
Data generated from naturally occurring processes tends to be non-stationary.