Skip to main content

Research Repository

Advanced Search

Outputs (276)

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.

The role of population size in folk tune complexity (preprint) (2021)
Journal Article
Street, S., Eerola, T., & Kendal, J. The role of population size in folk tune complexity (preprint). https://doi.org/10.31234/osf.io/2he8k. Manuscript submitted for publication

A positive correlation between population size and cultural complexity is perhaps one of the most consistent findings in the field of cultural evolution. However, previous findings are largely based on studies of technology and are not necessarily ge... Read More about The role of population size in folk tune complexity (preprint).

‘Now—For a Breath I Tarry’: Breath, Desire and Queer Materialism at the Fin de Siècle (2021)
Book Chapter
Riddell, F. (2021). ‘Now—For a Breath I Tarry’: Breath, Desire and Queer Materialism at the Fin de Siècle. In C. Saunders, D. Fuller, & J. Macnaughton (Eds.), The Life of Breath in Literature, Culture and Medicine: Classical to Contemporary (345-365). (1). Palgrave Macmillan. https://doi.org/10.1007/978-3-030-74443-4_17

Riddell explores how tropes of breath and breathlessness articulate the relationship between materiality, desire, and loss for queer subjects in Victorian literature. The essay presents readings of A. E. Housman’s A Shropshire Lad, John Addington Sym... Read More about ‘Now—For a Breath I Tarry’: Breath, Desire and Queer Materialism at the Fin de Siècle.

A Generative Bayesian Graph Attention Network for Semi-supervised Classification on Scarce Data (2021)
Presentation / Conference Contribution
Sun, Z., Harit, A., Yu, J., Cristea, A., & Al Moubayed, N. (2021, July). A Generative Bayesian Graph Attention Network for Semi-supervised Classification on Scarce Data. Presented at IEEE International Joint Conference on Neural Network (IJCNN2021), Virtual

This research focuses on semi-supervised classification tasks, specifically for graph-structured data under datascarce situations. It is known that the performance of conventional supervised graph convolutional models is mediocre at classification ta... Read More about A Generative Bayesian Graph Attention Network for Semi-supervised Classification on Scarce Data.

Curvature-based feature selection with application in classifying electronic health records (2021)
Journal Article
Zuo, Z., Li, J., Xu, H., & Al Moubayed, N. (2021). Curvature-based feature selection with application in classifying electronic health records. Technological Forecasting and Social Change, 173, Article 121127. https://doi.org/10.1016/j.techfore.2021.121127

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. As a powerful tool, ML... Read More about Curvature-based feature selection with application in classifying electronic health records.

ExBERT: An External Knowledge Enhanced BERT for Natural Language Inference (2021)
Book Chapter
Gajbhiye, A., Al Moubayed, N., & Bradley, S. (2021). ExBERT: An External Knowledge Enhanced BERT for Natural Language Inference. In I. Farkaš, P. Masulli, S. Otte, & S. Wermter (Eds.), Artificial Neural Networks and Machine Learning – ICANN 2021 30th International Conference on Artificial Neural Networks, Bratislava, Slovakia, September 14–17, 2021, Proceedings, Part V (460-472). Springer Verlag. https://doi.org/10.1007/978-3-030-86383-8_37

Neural language representation models such as BERT, pretrained on large-scale unstructured corpora lack explicit grounding to real-world commonsense knowledge and are often unable to remember facts required for reasoning and inference. Natural Langua... Read More about ExBERT: An External Knowledge Enhanced BERT for Natural Language Inference.

Notating Deconstruction: What Can Ethnomusicological Transcription Learn from the Notational Practices of Contemporary Composers? (2021)
Journal Article
Warren, M. (2021). Notating Deconstruction: What Can Ethnomusicological Transcription Learn from the Notational Practices of Contemporary Composers?. Journal of the Royal Musical Association, 146(2), 283-314. https://doi.org/10.1017/rma.2021.15

Drawing on Jacques Derrida’s (1981) approach to deconstructing Platonic dichotomies, this article argues that any notational system is inherently structuring and should be subjected to deconstructive efforts. Further, my contention is that this decon... Read More about Notating Deconstruction: What Can Ethnomusicological Transcription Learn from the Notational Practices of Contemporary Composers?.

Conformity to Bergmann's rule in birds depends on nest design and migration (2021)
Journal Article
Mainwaring, M. C., & Street, S. E. (2021). Conformity to Bergmann's rule in birds depends on nest design and migration. Ecology and Evolution, 11(19), 13118-13127. https://doi.org/10.1002/ece3.8034

Ecogeographical rules attempt to explain large-scale spatial patterns in biological traits. One of the most enduring examples is Bergmann's rule, which states that species should be larger in colder climates due to the thermoregulatory advantages of... Read More about Conformity to Bergmann's rule in birds depends on nest design and migration.