Nils Hammerla
YOU?
Author Swipe
View article: Harnessing Preference Optimisation in Protein LMs for Hit Maturation in Cell Therapy
Harnessing Preference Optimisation in Protein LMs for Hit Maturation in Cell Therapy Open
Cell and immunotherapy offer transformative potential for treating diseases like cancer and autoimmune disorders by modulating the immune system. The development of these therapies is resource-intensive, with the majority of drug candidate…
View article: Causally-guided Regularization of Graph Attention Improves Generalizability
Causally-guided Regularization of Graph Attention Improves Generalizability Open
Graph attention networks estimate the relational importance of node neighbors to aggregate relevant information over local neighborhoods for a prediction task. However, the inferred attentions are vulnerable to spurious correlations and co…
View article: Graph Neural Networks for Link Prediction with Subgraph Sketching
Graph Neural Networks for Link Prediction with Subgraph Sketching Open
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 to count triangles (the backbone of most LP heuristics) and …
View article: Towards more patient friendly clinical notes through language models and ontologies
Towards more patient friendly clinical notes through language models and ontologies Open
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 with valuable information about their health, while saving …
View article: Towards more patient friendly clinical notes through language models and ontologies.
Towards more patient friendly clinical notes through language models and ontologies. Open
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 with valuable information about their health, while saving …
View article: Neural Temporal Point Processes For Modelling Electronic Health Records
Neural Temporal Point Processes For Modelling Electronic Health Records Open
The modelling of Electronic Health Records (EHRs) has the potential to drive more efficient allocation of healthcare resources, enabling early intervention strategies and advancing personalised healthcare. However, EHRs are challenging to …
View article: Biomedical Concept Relatedness – A large EHR-based benchmark
Biomedical Concept Relatedness – A large EHR-based benchmark Open
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 consultation or to recruit suitable patients for a study. This …
View article: Estimating Mutual Information Between Dense Word Embeddings
Estimating Mutual Information Between Dense Word Embeddings Open
Word embedding-based similarity measures are currently among the top-performing methods on unsupervised semantic textual similarity (STS) tasks. Recent work has increasingly adopted a statistical view on these embeddings, with some of the …
View article: Correlations between Word Vector Sets
Correlations between Word Vector Sets Open
Similarity measures based purely on word embeddings are comfortably competing with much more sophisticated deep learning and expert-engineered systems on unsupervised semantic textual similarity (STS) tasks. In contrast to commonly used ge…
View article: Neural Language Priors
Neural Language Priors Open
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 architectures by holding them randomly initialised and fixed, effe…
View article: Correlation Coefficients and Semantic Textual Similarity
Correlation Coefficients and Semantic Textual Similarity Open
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 and many clever tricks. By contrast, little attention has b…
View article: Model Comparison for Semantic Grouping
Model Comparison for Semantic Grouping Open
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 task in which we contrast a generative model which jointly …
View article: Don't Settle for Average, Go for the Max: Fuzzy Sets and Max-Pooled Word Vectors
Don't Settle for Average, Go for the Max: Fuzzy Sets and Max-Pooled Word Vectors Open
Recent literature suggests that averaged word vectors followed by simple post-processing outperform many deep learning methods on semantic textual similarity tasks. Furthermore, when averaged word vectors are trained supervised on large co…
View article: Don't Settle for Average, Go for the Max: Fuzzy Sets and Max-Pooled Word Vectors.
Don't Settle for Average, Go for the Max: Fuzzy Sets and Max-Pooled Word Vectors. Open
Recent literature suggests that averaged word vectors followed by simple post-processing outperform many deep learning methods on semantic textual similarity tasks. Furthermore, when averaged word vectors are trained supervised on large co…
View article: Relational Graph Attention Networks
Relational Graph Attention Networks Open
We investigate Relational Graph Attention Networks, a class of models that extends non-relational graph attention mechanisms to incorporate relational information, opening up these methods to a wider variety of problems. A thorough evaluat…
View article: Correlation Coefficients and Semantic Textual Similarity
Correlation Coefficients and Semantic Textual Similarity Open
Vitalii Zhelezniak, Aleksandar Savkov, April Shen, Nils Hammerla. Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Pape…
View article: Multilingual Factor Analysis
Multilingual Factor Analysis Open
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 equivalent words in different languages as different …
View article: Correlations between Word Vector Sets
Correlations between Word Vector Sets Open
Vitalii Zhelezniak, April Shen, Daniel Busbridge, Aleksandar Savkov, Nils Hammerla. Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Proce…
View article: Decoding Decoders: Finding Optimal Representation Spaces for Unsupervised Similarity Tasks
Decoding Decoders: Finding Optimal Representation Spaces for Unsupervised Similarity Tasks Open
Experimental evidence indicates that simple models outperform complex deep networks on many unsupervised similarity tasks. We provide a simple yet rigorous explanation for this behaviour by introducing the concept of an optimal representat…
View article: Attention U-Net: Learning Where to Look for the Pancreas
Attention U-Net: Learning Where to Look for the Pancreas Open
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 implicitly learn to suppress irrelevant regions in an input image…
View article: Decoding Decoders: Finding Optimal Representation Spaces for Unsupervised Similarity Tasks
Decoding Decoders: Finding Optimal Representation Spaces for Unsupervised Similarity Tasks Open
Experimental evidence indicates that simple models outperform complex deep networks on many unsupervised similarity tasks. We provide a simple yet rigorous explanation for this behaviour by introducing the concept of an optimal representat…
View article: Offline bilingual word vectors, orthogonal transformations and the inverted softmax
Offline bilingual word vectors, orthogonal transformations and the inverted softmax Open
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 transformation, using dictionaries compiled from expert knowledge. In…
View article: Large Scale Population Assessment of Physical Activity Using Wrist Worn Accelerometers: The UK Biobank Study
Large Scale Population Assessment of Physical Activity Using Wrist Worn Accelerometers: The UK Biobank Study Open
BACKGROUND: Physical activity has not been objectively measured in prospective cohorts with sufficiently large numbers to reliably detect associations with multiple health outcomes. Technological advances now make this possible. We describ…
View article: A study of wrist-worn activity measurement as a potential real-world biomarker for late-life depression
A study of wrist-worn activity measurement as a potential real-world biomarker for late-life depression Open
Background Late-life depression (LLD) is associated with a decline in physical activity. Typically this is assessed by self-report questionnaires and, more recently, with actigraphy. We sought to explore the utility of a bespoke activity m…
View article: Sorting out symptoms: design and evaluation of the 'babylon check' automated triage system
Sorting out symptoms: design and evaluation of the 'babylon check' automated triage system Open
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 differential diagnosis based on the symptoms elucidated fr…
View article: Expressy
Expressy Open
Expressiveness, which we define as the extent to which rich and complex intent can be conveyed through action, is a vital aspect of many human interactions. For instance, paint on canvas is said to be an expressive medium, because it affor…
View article: Deep, Convolutional, and Recurrent Models for Human Activity Recognition using Wearables
Deep, Convolutional, and Recurrent Models for Human Activity Recognition using Wearables Open
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 feature extraction and classification techniques. From these isol…
View article: Diri - the actuated helium balloon
Diri - the actuated helium balloon Open
Research on actuated interfaces has shown that people respond in certain socialized ways to interfaces that exhibit autonomous behaviours. We wished to explore the elements of design that drive people to regard an autonomous, interactive s…