no code implementations • LREC 2022 • Isaac Ampomah, James Burton, Amir Enshaei, Noura Al Moubayed
This paper proposes a new natural language generation (NLG) task where neural models are trained to generate textual explanations, analytically describing the classification performance of ML models based on the metrics’ scores reported in the tables.
no code implementations • 28 May 2024 • Junjie Shentu, Matthew Watson, Noura Al Moubayed
In particular, our method leverages self-attention and cross-attention maps to create accurate masks for each concept within a single initialization step, omitting any required mask preparation by humans or other models.
1 code implementation • 9 Apr 2024 • Chenghao Xiao, G Thomas Hudson, Noura Al Moubayed
Under the emerging Retrieval-augmented Generation (RAG) paradigm, we envision the need to evaluate next-level language understanding abilities of embedding models, and take a conscious look at the reasoning abilities stored in them.
no code implementations • 29 Mar 2024 • Seyma Yucer, Amir Atapour Abarghouei, Noura Al Moubayed, Toby P. Breckon
Achieving an effective fine-grained appearance variation over 2D facial images, whilst preserving facial identity, is a challenging task due to the high complexity and entanglement of common 2D facial feature encoding spaces.
1 code implementation • 15 Feb 2024 • Junjie Shentu, Matthew Watson, Noura Al Moubayed
Subject-driven text-to-image diffusion models empower users to tailor the model to new concepts absent in the pre-training dataset using a few sample images.
1 code implementation • 13 Feb 2024 • Chenghao Xiao, Zhuoxu Huang, Danlu Chen, G Thomas Hudson, Yizhi Li, Haoran Duan, Chenghua Lin, Jie Fu, Jungong Han, Noura Al Moubayed
To our knowledge, this is the first representation learning method devoid of traditional language models for understanding sentence and document semantics, marking a stride closer to human-like textual comprehension.
1 code implementation • 24 Jan 2024 • Siwei Wu, Yizhi Li, Kang Zhu, Ge Zhang, Yiming Liang, Kaijing Ma, Chenghao Xiao, Haoran Zhang, Bohao Yang, Wenhu Chen, Wenhao Huang, Noura Al Moubayed, Jie Fu, Chenghua Lin
We further annotate the image-text pairs with two-level subset-subcategory hierarchy annotations to facilitate a more comprehensive evaluation of the baselines.
1 code implementation • 24 Oct 2023 • Chenghao Xiao, Yizhi Li, G Thomas Hudson, Chenghua Lin, Noura Al Moubayed
In recent years, contrastive learning (CL) has been extensively utilized to recover sentence and document-level encoding capability from pre-trained language models.
no code implementations • 21 Sep 2023 • Yang Wang, Qibin Liang, Chenghao Xiao, Yizhi Li, Noura Al Moubayed, Chenghua Lin
Audio classification plays a crucial role in speech and sound processing tasks with a wide range of applications.
no code implementations • 1 May 2023 • Seyma Yucer, Furkan Tektas, Noura Al Moubayed, Toby P. Breckon
Facial recognition is one of the most academically studied and industrially developed areas within computer vision where we readily find associated applications deployed globally.
1 code implementation • 5 Jan 2023 • Jialin Yu, Alexandra I. Cristea, Anoushka Harit, Zhongtian Sun, Olanrewaju Tahir Aduragba, Lei Shi, Noura Al Moubayed
To leverage information from text pairs, we additionally introduce a novel supervised model we call dual directional learning (DDL), which is designed to integrate with our proposed VSAR model.
1 code implementation • 18 Dec 2022 • Chenghao Xiao, Yang Long, Noura Al Moubayed
In this paper, we aim to help guide future designs of sentence representation learning methods by taking a closer look at contrastive SRL through the lens of isotropy, contextualization and learning dynamics.
no code implementations • 2 Nov 2022 • Peng Zhang, Yawen Huang, Bingzhang Hu, Shizheng Wang, Haoran Duan, Noura Al Moubayed, Yefeng Zheng, Yang Long
Reinforcement Learning (RL)-based control system has received considerable attention in recent decades.
no code implementations • 2 Sep 2022 • Jialin Yu, Alexandra I. Cristea, Anoushka Harit, Zhongtian Sun, Olanrewaju Tahir Aduragba, Lei Shi, Noura Al Moubayed
XAI with natural language processing aims to produce human-readable explanations as evidence for AI decision-making, which addresses explainability and transparency.
Decision Making Explainable Artificial Intelligence (XAI) +2
no code implementations • 16 Aug 2022 • Seyma Yucer, Matt Poyser, Noura Al Moubayed, Toby P. Breckon
Yes - This study investigates the impact of commonplace lossy image compression on face recognition algorithms with regard to the racial characteristics of the subject.
1 code implementation • 7 Aug 2022 • Xiatian Zhang, Noura Al Moubayed, Hubert P. H. Shum
Hence, we propose a graph representation learning framework to comprehensively represent instrument motions in the surgical workflow anticipation problem.
1 code implementation • 24 Mar 2022 • Daniel Kluvanec, Thomas B. Phillips, Kenneth J. W. McCaffrey, Noura Al Moubayed
Instead, we separate the chromosome instances in a second stage, predicting the orientation of the chromosomes by the model and use it as one of the key distinguishing factors of the chromosomes.
1 code implementation • LREC 2022 • G Thomas Hudson, Noura Al Moubayed
The impressive progress in NLP techniques has been driven by the development of multi-task benchmarks such as GLUE and SuperGLUE.
Ranked #1 on Translation on MuLD (OpenSubtitles)
1 code implementation • PeerJ Computer Science 2021 • G. Thomas Hudson, Noura Al Moubayed
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.
1 code implementation • 19 Oct 2021 • Seyma Yucer, Furkan Tektas, Noura Al Moubayed, Toby P. Breckon
We use the set of observable characteristics of an individual face where a race-related facial phenotype is hence specific to the human face and correlated to the racial profile of the subject.
no code implementations • 3 Aug 2021 • Amit Gajbhiye, Noura Al Moubayed, Steven Bradley
We introduce a new model for NLI called External Knowledge Enhanced BERT (ExBERT), to enrich the contextual representation with real-world commonsense knowledge from external knowledge sources and enhance BERT's language understanding and reasoning capabilities.
no code implementations • ACL (GeBNLP) 2021 • Elizabeth Excell, Noura Al Moubayed
We then apply the learned associations between gender and language to toxic language classifiers, finding that models trained exclusively on female-annotated data perform 1. 8% better than those trained solely on male-annotated data and that training models on data after removing all offensive words reduces bias in the model by 55. 5% while increasing the sensitivity by 0. 4%.
1 code implementation • 14 May 2021 • Matthew Watson, Bashar Awwad Shiekh Hasan, Noura Al Moubayed
Deep Learning of neural networks has progressively become more prominent in healthcare with models reaching, or even surpassing, expert accuracy levels.
1 code implementation • 5 May 2021 • Matthew Watson, Noura Al Moubayed
On the MIMIC-III and Henan-Renmin EHR datasets, we report a detection accuracy of 77% against the Longitudinal Adversarial Attack.
1 code implementation • 10 Jan 2021 • Zheming Zuo, Jie Li, Han Xu, Noura Al Moubayed
Disruptive technologies provides unparalleled opportunities to contribute to the identifications of many aspects in pervasive healthcare, from the adoption of the Internet of Things through to Machine Learning (ML) techniques.
no code implementations • 18 Dec 2020 • Thomas Winterbottom, Sarah Xiao, Alistair McLean, Noura Al Moubayed
We share our results on the TVQA baseline model, and the recently proposed heterogeneous-memory-enchanced multimodal attention (HME) model.
1 code implementation • 18 Dec 2020 • Thomas Winterbottom, Sarah Xiao, Alistair McLean, Noura Al Moubayed
Our results demonstrate that models trained on only the visual information can answer ~45% of the questions, while using only the subtitles achieves ~68%.
no code implementations • 22 Oct 2020 • Amit Gajbhiye, Thomas Winterbottom, Noura Al Moubayed, Steven Bradley
BiCAM incorporates real-world commonsense knowledge into NLI models.
1 code implementation • 15 Jan 2019 • Nik Khadijah Nik Aznan, Amir Atapour-Abarghouei, Stephen Bonner, Jason Connolly, Noura Al Moubayed, Toby Breckon
Despite significant recent progress in the area of Brain-Computer Interface (BCI), there are numerous shortcomings associated with collecting Electroencephalography (EEG) signals in real-world environments.
Quantitative Methods Signal Processing
no code implementations • 22 Oct 2018 • Amit Gajbhiye, Sardar Jaf, Noura Al Moubayed, A. Stephen McGough, Steven Bradley
In this paper, we propose a novel RNN model for NLI and empirically evaluate the effect of applying dropout at different layers in the model.
no code implementations • 19 Oct 2018 • A. Stephen McGough, Matthew Forshaw, John Brennan, Noura Al Moubayed, Stephen Bonner
We demonstrate, through the use of simulation, how we can reduce this wasted energy by targeting tasks at computers less likely to be needed for primary use, predicting this idle time through machine learning.
no code implementations • 17 Jun 2016 • Noura Al Moubayed, Toby Breckon, Peter Matthews, A. Stephen McGough
In This paper we present a novel approach to spam filtering and demonstrate its applicability with respect to SMS messages.