Outputs (4)

Bilinear Fusion of Commonsense Knowledge with Attention-Based NLI Models (2020)
Book Chapter
Gajbhiye, A., Winterbottom, T., Al Moubayed, N., & Bradley, S. (2020). Bilinear Fusion of Commonsense Knowledge with Attention-Based NLI Models. In I. Farkaš, P. Masulli, & S. Wermter (Eds.), Artificial Neural Networks and Machine Learning – ICANN 2020 (633-646). Springer Verlag. https://doi.org/10.1007/978-3-030-61609-0_50

We consider the task of incorporating real-world commonsense knowledge into deep Natural Language Inference (NLI) models. Existing external knowledge incorporation methods are limited to lexical-level knowledge and lack generalization across NLI mode... Read More about Bilinear Fusion of Commonsense Knowledge with Attention-Based NLI Models.

On Modality Bias in the TVQA Dataset (2020)
Presentation / Conference Contribution
Winterbottom, T., Xiao, S., McLean, A., & Al Moubayed, N. (2020, September). On Modality Bias in the TVQA Dataset. Presented at The British Machine Vision Conference (BMVC), Manchester, England

TVQA is a large scale video question answering (video-QA) dataset based on popular TV shows. The questions were specifically designed to require “both vision and language understanding to answer”. In this work, we demonstrate an inherent bias in the... Read More about On Modality Bias in the TVQA Dataset.

Exploring Racial Bias within Face Recognition via per-subject Adversarially-Enabled Data Augmentation (2020)
Presentation / Conference Contribution
Yucer, S., Akcay, S., Al Moubayed, N., & Breckon, T. (2020, June). Exploring Racial Bias within Face Recognition via per-subject Adversarially-Enabled Data Augmentation. Presented at Computer Vision and Pattern Recognition Workshops, Seattle, USA

Beyond the topics: how deep learning can improve the discriminability of probabilistic topic modelling (2020)
Journal Article
Al Moubayed, N., McGough, S., & Awwad Shiekh Hasan, B. (2020). Beyond the topics: how deep learning can improve the discriminability of probabilistic topic modelling. PeerJ Computer Science, 6, Article e252. https://doi.org/10.7717/peerj-cs.252

The article presents a discriminative approach to complement the unsupervised probabilistic nature of topic modelling. The framework transforms the probabilities of the topics per document into class-dependent deep learning models that extract highly... Read More about Beyond the topics: how deep learning can improve the discriminability of probabilistic topic modelling.