4.6k citations · 5.5k across the 15 of their papers we have counts for
18 papers
Causally-guided Regularization of Graph Attention Improves Generalizability
Alexander P. Wu, Thomas Markovich, Bonnie Berger +2
Graph attention networks estimate the relational importance of node neighbors to aggregate relevant information over local neighborhoods for a prediction task. However, the inferre…
Graph Neural Networks for Link Prediction with Subgraph Sketching
Benjamin Paul Chamberlain, Sergey Shirobokov, Emanuele Rossi +5
Many Graph Neural Networks (GNNs) perform poorly compared to simple heuristics on Link Prediction (LP) tasks. This is due to limitations in expressive power such as the inability t…
Towards more patient friendly clinical notes through language models and ontologies
Francesco Moramarco, Damir Juric, Aleksandar Savkov +8
Clinical notes are an efficient way to record patient information but are notoriously hard to decipher for non-experts. Automatically simplifying medical text can empower patients…
Biomedical Concept Relatedness -- A large EHR-based benchmark
Claudia Schulz, Josh Levy-Kramer, Camille Van Assel +2
A promising application of AI to healthcare is the retrieval of information from electronic health records (EHRs), e.g. to aid clinicians in finding relevant information for a cons…
Neural Temporal Point Processes For Modelling Electronic Health Records
Joseph Enguehard, Dan Busbridge, Adam Bozson +2
The modelling of Electronic Health Records (EHRs) has the potential to drive more efficient allocation of healthcare resources, enabling early intervention strategies and advancing…
Correlations between Word Vector Sets
Vitalii Zhelezniak, April Shen, Daniel Busbridge +2
Similarity measures based purely on word embeddings are comfortably competing with much more sophisticated deep learning and expert-engineered systems on unsupervised semantic text…
Neural Language Priors
Joseph Enguehard, Dan Busbridge, Vitalii Zhelezniak +1
The choice of sentence encoder architecture reflects assumptions about how a sentence's meaning is composed from its constituent words. We examine the contribution of these archite…
Explaining Deep Learning Models with Constrained Adversarial Examples
Jonathan Moore, Nils Hammerla, Chris Watkins
Machine learning algorithms generally suffer from a problem of explainability. Given a classification result from a model, it is typically hard to determine what caused the decisio…
Correlation Coefficients and Semantic Textual Similarity
Vitalii Zhelezniak, Aleksandar Savkov, April Shen +1
A large body of research into semantic textual similarity has focused on constructing state-of-the-art embeddings using sophisticated modelling, careful choice of learning signals…
Multilingual Factor Analysis
Francisco Vargas, Kamen Brestnichki, Alex Papadopoulos-Korfiatis +1
In this work we approach the task of learning multilingual word representations in an offline manner by fitting a generative latent variable model to a multilingual dictionary. We…
Model Comparison for Semantic Grouping
Francisco Vargas, Kamen Brestnichki, Nils Hammerla
We introduce a probabilistic framework for quantifying the semantic similarity between two groups of embeddings. We formulate the task of semantic similarity as a model comparison…
Don't Settle for Average, Go for the Max: Fuzzy Sets and Max-Pooled Word Vectors
Vitalii Zhelezniak, Aleksandar Savkov, April Shen +3
Recent literature suggests that averaged word vectors followed by simple post-processing outperform many deep learning methods on semantic textual similarity tasks. Furthermore, wh…
Relational Graph Attention Networks
Dan Busbridge, Dane Sherburn, Pietro Cavallo +1
We investigate Relational Graph Attention Networks, a class of models that extends non-relational graph attention mechanisms to incorporate relational information, opening up these…
Attention U-Net: Learning Where to Look for the Pancreas
Ozan Oktay, Jo Schlemper, Loic Le Folgoc +9
We propose a novel attention gate (AG) model for medical imaging that automatically learns to focus on target structures of varying shapes and sizes. Models trained with AGs implic…
Decoding Decoders: Finding Optimal Representation Spaces for Unsupervised Similarity Tasks
Vitalii Zhelezniak, Dan Busbridge, April Shen +2
Experimental evidence indicates that simple models outperform complex deep networks on many unsupervised similarity tasks. We provide a simple yet rigorous explanation for this beh…
Offline bilingual word vectors, orthogonal transformations and the inverted softmax
Samuel L. Smith, David H. P. Turban, Steven Hamblin +1
Usually bilingual word vectors are trained "online". Mikolov et al. showed they can also be found "offline", whereby two pre-trained embeddings are aligned with a linear transforma…
Sorting out symptoms: design and evaluation of the 'babylon check' automated triage system
Katherine Middleton, Mobasher Butt, Nils Hammerla +3
Prior to seeking professional medical care it is increasingly common for patients to use online resources such as automated symptom checkers. Many such systems attempt to provide a…
Deep, Convolutional, and Recurrent Models for Human Activity Recognition using Wearables
Nils Y. Hammerla, Shane Halloran, Thomas Ploetz
Human activity recognition (HAR) in ubiquitous computing is beginning to adopt deep learning to substitute for well-established analysis techniques that rely on hand-crafted featur…