A Stable Variational Autoencoder for Text Modelling

Autor: Li, Ruizhe, Li, Xiao, Lin, Chenghua, Collinson, Matthew, Mao, Rui

Variational Autoencoder (VAE) is a powerful method for learning representations of high-dimensional data. However, VAEs can suffer from an issue known as latent variable collapse (or KL loss vanishing), where the posterior collapses to the prior and

Externí odkaz: http://arxiv.org/abs/1911.05343

Maintaining fidelity to the treatment court model through evaluation: The racial and ethnic disparities (RED) program assessment tool.

Autor: Gallagher, John R.¹ (AUTHOR) jgalla9@gmu.edu, Collinson, Matthew R.² (AUTHOR), Francis, Zephi² (AUTHOR)

Publikováno v: Journal of Human Behavior in the Social Environment. Aug2024, p1-12. 12p.

The effect of type of mechanical processing on electrical conductivity and piezoresistive response of CNT and graphite composites

Autor: Collinson, Matthew, Hayes, Simon, Petropoulos, Stefanos

Publikováno v: In Procedia CIRP 2019 85:314-320

Exploring susceptibility measures to persuasion

Autor: Vargheese, John Paul, Collinson, Matthew, Masthoff, Judith, Gram-Hansen, Sandra, Svarre, Tanja, Midden, Cees, Sub Human-Centered Computing, Human-Centered Computing

Publikováno v: Persuasive Technology. Designing for Future Change, 16. Springer Cham
STARTPAGE=16;TITLE=Persuasive Technology. Designing for Future Change
Lecture Notes in Computer Science ISBN: 9783030457112
PERSUASIVE

There is increasing evidence that indicates how personalising persuasive strategies may increase the effectiveness of persuasive technologies and behaviour change interventions. This has led to a wide range of studies exploring self reported, perceiv

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::cd6a87ed59ed1098550d042a6c166a36
https://dspace.library.uu.nl/handle/1874/396210

A Dual-Attention Hierarchical Recurrent Neural Networkfor Dialogue Act Classification

Autor: Li, Ruizhe, Lin, Chenghua, Collinson, Matthew, Li, Xiao, Chen, G.

Recognising dialogue acts (DA) is important for many natural language processing tasks such as dialogue generation and intention recognition. In this paper, we propose a dual-attention hierarchical recurrent neural network for DA classification. Our

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=od_______101::d38c5223a170c1f80ef26d12f7432e42
https://dspace.library.uu.nl/handle/1874/390083