Language as a latent sequence: Deep latent variable models for semi-supervised paraphrase generation (2023)
Journal Article
Yu, J., Cristea, A. I., Harit, A., Sun, Z., Aduragba, O. T., Shi, L., & Al Moubayed, N. (2023). Language as a latent sequence: Deep latent variable models for semi-supervised paraphrase generation. AI open, 4, 19-32. https://doi.org/10.1016/j.aiopen.2023.05.001

This paper explores deep latent variable models for semi-supervised paraphrase generation, where the missing target pair for unlabelled data is modelled as a latent paraphrase sequence. We present a novel unsupervised model named variational sequence... Read More about Language as a latent sequence: Deep latent variable models for semi-supervised paraphrase generation.

Negation Invariant Representations of 3D Vectors for Deep Learning Models applied to Fault Geometry Mapping in 3D Seismic Reflection Data (2023)
Journal Article
Kluvanec, D., McCaffrey, K. J., Phillips, T. B., & Al Moubayed, N. (2023). Negation Invariant Representations of 3D Vectors for Deep Learning Models applied to Fault Geometry Mapping in 3D Seismic Reflection Data. IEEE Transactions on Geoscience and Remote Sensing, https://doi.org/10.1109/tgrs.2023.3273329

We can represent the orientation of a plane in 3D by its normal vector. However, every plane has two normal vectors that are negatives of each other. We propose four novel representations of vectors in 3D that are negation invariant and can be used b... Read More about Negation Invariant Representations of 3D Vectors for Deep Learning Models applied to Fault Geometry Mapping in 3D Seismic Reflection Data.

Is Unimodal Bias Always Bad for Visual Question Answering? A Medical Domain Study with Dynamic Attention (2022)
Conference Proceeding
Sun, Z., Harit, A., Cristea, A. I., Yu, J., Al Moubayed, N., & Shi, L. (2022). Is Unimodal Bias Always Bad for Visual Question Answering? A Medical Domain Study with Dynamic Attention. . https://doi.org/10.1109/bigdata55660.2022.10020791

Medical visual question answering (Med-VQA) is to answer medical questions based on clinical images provided. This field is still in its infancy due to the complexity of the trio formed of questions, multimodal features and expert knowledge. In this... Read More about Is Unimodal Bias Always Bad for Visual Question Answering? A Medical Domain Study with Dynamic Attention.

Using Model Explanations to Guide Deep Learning Models Towards Consistent Explanations for EHR Data (2022)
Journal Article
Watson, M., Awwad Shekh Hasan, B., & Al Moubayed, N. (2022). Using Model Explanations to Guide Deep Learning Models Towards Consistent Explanations for EHR Data. Scientific Reports, 12(19899), Article 19899. https://doi.org/10.1038/s41598-022-24356-6

It has been shown that identical Deep Learning (DL) architectures will produce distinct explanations when trained with different hyperparameters that are orthogonal to the task (e.g. random seed, training set order). In domains such as healthcare and... Read More about Using Model Explanations to Guide Deep Learning Models Towards Consistent Explanations for EHR Data.

Towards Graph Representation Learning Based Surgical Workflow Anticipation (2022)
Conference Proceeding
Zhang, X., Al Moubayed, N., & Shum, H. P. (2022). Towards Graph Representation Learning Based Surgical Workflow Anticipation. . https://doi.org/10.1109/bhi56158.2022.9926801

Surgical workflow anticipation can give predictions on what steps to conduct or what instruments to use next, which is an essential part of the computer-assisted intervention system for surgery, e.g. workflow reasoning in robotic surgery. However, cu... Read More about Towards Graph Representation Learning Based Surgical Workflow Anticipation.

Does lossy image compression affect racial bias within face recognition? (2022)
Conference Proceeding
Yucer, S., Poyser, M., Al Moubayed, N., & Breckon, T. (2022). Does lossy image compression affect racial bias within face recognition?.

This study investigates the impact of commonplace lossy image compression on face recognition algorithms with regard to the racial characteristics of the subject. We adopt a recently proposed racial phenotype-based bias analysis methodology to measur... Read More about Does lossy image compression affect racial bias within face recognition?.

Efficient Uncertainty Quantification for Multilabel Text Classification (2022)
Conference Proceeding
Yu, J., Cristea, A. I., Harit, A., Sun, Z., Aduragba, O. T., Shi, L., & Al Moubayed, N. (2022). Efficient Uncertainty Quantification for Multilabel Text Classification. . https://doi.org/10.1109/ijcnn55064.2022.9892871

Despite rapid advances of modern artificial intelligence (AI), there is a growing concern regarding its capacity to be explainable, transparent, and accountable. One crucial step towards such AI systems involves reliable and efficient uncertainty qua... Read More about Efficient Uncertainty Quantification for Multilabel Text Classification.

Contrastive Learning with Heterogeneous Graph Attention Networks on Short Text Classification (2022)
Conference Proceeding
Sun, Z., Harit, A., Cristea, A. I., Yu, J., Shi, L., & Al Moubayed, N. (2022). Contrastive Learning with Heterogeneous Graph Attention Networks on Short Text Classification. . https://doi.org/10.1109/ijcnn55064.2022.9892257

Graph neural networks (GNNs) have attracted extensive interest in text classification tasks due to their expected superior performance in representation learning. However, most existing studies adopted the same semi-supervised learning setting as the... Read More about Contrastive Learning with Heterogeneous Graph Attention Networks on Short Text Classification.

INTERACTION: A Generative XAI Framework for Natural Language Inference Explanations (2022)
Conference Proceeding
Yu, J., Cristea, A. I., Harit, A., Sun, Z., Aduragba, O. T., Shi, L., & Al Moubayed, N. (2022). INTERACTION: A Generative XAI Framework for Natural Language Inference Explanations. . https://doi.org/10.1109/ijcnn55064.2022.9892336

XAI with natural language processing aims to produce human-readable explanations as evidence for AI decisionmaking, which addresses explainability and transparency. However, from an HCI perspective, the current approaches only focus on delivering a s... Read More about INTERACTION: A Generative XAI Framework for Natural Language Inference Explanations.

In-Materio Extreme Learning Machines (2022)
Book Chapter
Jones, B. A., Al Moubayed, N., Zeze, D. A., & Groves, C. (2022). In-Materio Extreme Learning Machines. In G. Rudolph, A. V. Kononova, H. Aguirre, P. Kerschke, G. Ochoa, & T. Tušar (Eds.), Parallel Problem Solving from Nature – PPSN XVII (505-519). Springer Verlag. https://doi.org/10.1007/978-3-031-14714-2_35

Nanomaterial networks have been presented as a building block for unconventional in-Materio processors. Evolution in-Materio (EiM) has previously presented a way to congure and exploit physical materials for computation, but their ability to scale as... Read More about In-Materio Extreme Learning Machines.

Towards Intelligently Designed Evolvable Processors (2022)
Journal Article
Jones, B. A., Chouard, J. L., Branco, B. C., Vissol-Gaudin, E. G., Pearson, C., Petty, M. C., …Groves, C. (2022). Towards Intelligently Designed Evolvable Processors. Evolutionary Computation, 30(4), 479-501. https://doi.org/10.1162/evco_a_00309

Evolution-in-Materio is a computational paradigm in which an algorithm reconfigures a material’s properties to achieve a specific computational function. This paper addresses the question of how successful and well performing Evolution-in-Materio pro... Read More about Towards Intelligently Designed Evolvable Processors.

A deep learning approach to fight illicit trafficking of antiquities using artefact instance classification (2022)
Journal Article
Winterbottom, T., Leone, A., & Al Moubayed, N. (2022). A deep learning approach to fight illicit trafficking of antiquities using artefact instance classification. Scientific Reports, 12(1), Article 13468. https://doi.org/10.1038/s41598-022-15965-2

We approach the task of detecting the illicit movement of cultural heritage from a machine learning perspective by presenting a framework for detecting a known artefact in a new and unseen image. To this end, we explore the machine learning problem o... Read More about A deep learning approach to fight illicit trafficking of antiquities using artefact instance classification.

Generating Textual Explanations for Machine Learning Models Performance: A Table-to-Text Task (2022)
Conference Proceeding
Ampomah, I., Burton, J., Enshaei, A., & Al Moubayed, N. (2022). Generating Textual Explanations for Machine Learning Models Performance: A Table-to-Text Task. In C. Nicoletta, B. Frederic, B. Philippe, C. Khalid, C. Christopher, D. Thierry, …P. Stelios (Eds.),

Numerical tables are widely employed to communicate or report the classification performance of machine learning (ML) models with respect to a set of evaluation metrics. For non-experts, domain knowledge is required to fully understand and interpret... Read More about Generating Textual Explanations for Machine Learning Models Performance: A Table-to-Text Task.

MuLD: The Multitask Long Document Benchmark (2022)
Conference Proceeding
Hudson, G. T., & Al Moubayed, N. (2022). MuLD: The Multitask Long Document Benchmark. In N. Calzolari, F. Bechet, P. Blache, K. Choukri, C. Cieri, T. Declerck, …S. Piperidis (Eds.),

The impressive progress in NLP techniques has been driven by the development of multi-task benchmarks such as GLUE and SuperGLUE. While these benchmarks focus on tasks for one or two input sentences, there has been exciting work in designing efficien... Read More about MuLD: The Multitask Long Document Benchmark.

Bilinear Pooling in Video-QA: Empirical Challenges and Motivational Drift from Neurological Parallels (2022)
Journal Article
Winterbottom, T., Xiao, S., McLean, A., & Al Moubayed, N. (2022). Bilinear Pooling in Video-QA: Empirical Challenges and Motivational Drift from Neurological Parallels. PeerJ Computer Science, 8(e974), Article e974. https://doi.org/10.7717/peerj-cs.974

Bilinear pooling (BLP) refers to a family of operations recently developed for fusing features from different modalities predominantly for visual question answering (VQA) models. Successive BLP techniques have yielded higher performance with lower co... Read More about Bilinear Pooling in Video-QA: Empirical Challenges and Motivational Drift from Neurological Parallels.

ALADDIn: Autoencoder-LSTM based Anomaly Detector of Deformation in InSAR (2022)
Journal Article
Shakeel, A., Walters, R. J., Ebmeier, S. K., & Moubayed, N. A. (2022). ALADDIn: Autoencoder-LSTM based Anomaly Detector of Deformation in InSAR. IEEE Transactions on Geoscience and Remote Sensing, 60, https://doi.org/10.1109/tgrs.2022.3169455

In this study, we address the challenging problem of automatic detection of transient deformation of the Earth’s crust in time series of differential satellite radar [interferometric synthetic aperture radar (InSAR)] images. The detection of these ev... Read More about ALADDIn: Autoencoder-LSTM based Anomaly Detector of Deformation in InSAR.

Enhanced Methods for Evolution in-Materio Processors (2022)
Conference Proceeding
Jones, B. A., Al Moubayed, N., Zeze, D. A., & Groves, C. (2022). Enhanced Methods for Evolution in-Materio Processors. . https://doi.org/10.1109/icrc53822.2021.00026

Evolution-in-Materio (EiM) is an unconventional computing paradigm, which uses an Evolutionary Algorithm (EA) to configure a material's parameters so that it can perform a computational task. While EiM processors show promise, slow manufacturing and... Read More about Enhanced Methods for Evolution in-Materio Processors.

Measuring Hidden Bias within Face Recognition via Racial Phenotypes (2022)
Conference Proceeding
Yucer, S., Tekras, F., Al Moubayed, N., & Breckon, T. (2022). Measuring Hidden Bias within Face Recognition via Racial Phenotypes. . https://doi.org/10.1109/wacv51458.2022.00326

Recent work reports disparate performance for intersectional racial groups across face recognition tasks: face verification and identification. However, the definition of those racial groups has a significant impact on the underlying findings of such... Read More about Measuring Hidden Bias within Face Recognition via Racial Phenotypes.

Agree to Disagree: When Deep Learning Models With Identical Architectures Produce Distinct Explanations (2022)
Conference Proceeding
Watson, M., Awwad Shiekh Hasan, B., & Al Moubayed, N. (2022). Agree to Disagree: When Deep Learning Models With Identical Architectures Produce Distinct Explanations. . https://doi.org/10.1109/wacv51458.2022.00159

Deep Learning of neural networks has progressively become more prominent in healthcare with models reaching, or even surpassing, expert accuracy levels. However, these success stories are tainted by concerning reports on the lack of model transparenc... Read More about Agree to Disagree: When Deep Learning Models With Identical Architectures Produce Distinct Explanations.

Ask me in your own words: paraphrasing for multitask question answering (2021)
Journal Article
Hudson, G. T., & Al Moubayed, N. (2021). Ask me in your own words: paraphrasing for multitask question answering. PeerJ Computer Science, 7, Article e759. https://doi.org/10.7717/peerj-cs.759

Multitask learning has led to significant advances in Natural Language Processing, including the decaNLP benchmark where question answering is used to frame 10 natural language understanding tasks in a single model. In this work we show how models tr... Read More about Ask me in your own words: paraphrasing for multitask question answering.