Recent advances of powerful Language Models have allowed Natural Languag...
In Natural Language Generation (NLG) tasks, for any input, multiple
comm...
The lack of interpretability of the Vision Transformer may hinder its us...
Calibration is a popular framework to evaluate whether a classifier know...
We propose a framework for the statistical evaluation of variational
aut...
Generative approaches have been recently shown to be effective for both
...
In neural machine translation (NMT), we search for the mode of the model...
Neural networks and other machine learning models compute continuous
rep...
The factual knowledge acquired during pretraining and stored in the
para...
The detection and normalization of diseases in biomedical texts are key
...
Training neural network models with discrete (categorical or structured)...
Normalising flows (NFs) for discrete data are challenging because
parame...
There is a growing interest in probabilistic models defined in
hyper-sph...
Recent studies have revealed a number of pathologies of neural machine
t...
Attribution methods assess the contribution of inputs (e.g., words) to t...
Translation into morphologically-rich languages challenges neural machin...
The success of neural networks comes hand in hand with a desire for more...
Advances in variational inference enable parameterisation of probabilist...
Normalising flows (NFS) map two density functions via a differentiable
b...
Recently it was shown that linguistic structure predicted by a supervise...
In this work, we propose to model the interaction between visual and tex...
Most research in reading comprehension has focused on answering question...
We present a deep generative model of bilingual sentence pairs. The mode...
The process of translation is ambiguous, in that there are typically man...
This work exploits translation data as a source of semantically relevant...
We present a simple and effective approach to incorporating syntactic
st...
The University of Sheffield (USFD) participated in the International Wor...