• Publications
  • Influence
The Risk of Racial Bias in Hate Speech Detection
This work proposes *dialect* and *race priming* as ways to reduce the racial bias in annotation, showing that when annotators are made explicitly aware of an AAE tweet’s dialect they are significantly less likely to label the tweet as offensive. Expand
Show Your Work: Improved Reporting of Experimental Results
It is demonstrated that test-set performance scores alone are insufficient for drawing accurate conclusions about which model performs best, and a novel technique is presented: expected validation performance of the best-found model as a function of computation budget. Expand
The Media Frames Corpus: Annotations of Frames Across Issues
We describe the first version of the Media Frames Corpus: several thousand news articles on three policy issues, annotated in terms of media framing. We motivate framing as a phenomenon of study forExpand
Neural Models for Documents with Metadata
A general neural framework is proposed, based on topic models, to enable flexible incorporation of metadata and allow for rapid exploration of alternative models, and achieves strong performance, with a manageable tradeoff between perplexity, coherence, and sparsity. Expand
A Neural Framework for Generalized Topic Models
This paper combines certain motivating ideas behind variations on topic models with modern techniques for variational inference to produce a flexible framework for topic modeling that allows for rapid exploration of different models. Expand
Tracking the Development of Media Frames within and across Policy Issues
Framing is a central concept in political communication and a powerful political tool. Thus, it is hugely important to understand: a) what frames are used to define specific issues, b) what generalExpand
Metabolic mapping of deep brain structures and associations with symptomatology in autism spectrum disorders.
Using magnetic resonance spectroscopy, changes in deep gray matter neurochemistry are suggested, which are sensitive to diagnosis, age and sex, and are associated with behavioral differences. Expand
Variational Pretraining for Semi-supervised Text Classification
VAMPIRE is introduced, a lightweight pretraining framework for effective text classification when data and computing resources are limited and it is found that fine-tuning to in-domain data is crucial to achieving decent performance from contextual embeddings when working with limited supervision. Expand
Quantitative MRI in the very preterm brain: Assessing tissue organization and myelination using magnetization transfer, diffusion tensor and T1 imaging
The value of quantitative MRI for tracking brain maturation over the neonatal period is demonstrated and reported on the concordance with available histological data. Expand
Deep grey matter growth predicts neurodevelopmental outcomes in very preterm children
Deep grey matter growth rates are highlighted as promising biomarkers of long-term outcomes following very preterm birth, and contribute to the understanding of the brain-behaviour relations in these children. Expand