Search Results for author:
Found 14 papers, 6 papers with code
Understanding Fine-grained Distortions in Reports of Scientific Findings
Distorted science communication harms individuals and society as it can lead to unhealthy behavior change and decrease trust in scientific institutions.
Efficiency is Not Enough: A Critical Perspective of Environmentally Sustainable AI
The solution lionized by both industry and the ML community to improve the environmental sustainability of ML is to increase the efficiency with which ML systems operate in terms of both compute and energy consumption.
Multi-View Knowledge Distillation from Crowd Annotations for Out-of-Domain Generalization
Selecting an effective training signal for tasks in natural language processing is difficult: expert annotations are expensive, and crowd-sourced annotations may not be reliable.
Revisiting Softmax for Uncertainty Approximation in Text Classification
A cheaper alternative is to simply use the softmax based on a single forward pass without dropout to estimate model uncertainty.
Modeling Information Change in Science Communication with Semantically Matched Paraphrases
Whether the media faithfully communicate scientific information has long been a core issue to the science community.
Generating Scientific Claims for Zero-Shot Scientific Fact Checking
To address this challenge, we propose scientific claim generation, the task of generating one or more atomic and verifiable claims from scientific sentences, and demonstrate its usefulness in zero-shot fact checking for biomedical claims.
Semi-Supervised Exaggeration Detection of Health Science Press Releases
Given this, we present a formalization of and study into the problem of exaggeration detection in science communication.
CiteWorth: Cite-Worthiness Detection for Improved Scientific Document Understanding
Scientific document understanding is challenging as the data is highly domain specific and diverse.
Longitudinal Citation Prediction using Temporal Graph Neural Networks
Citation count prediction is the task of predicting the number of citations a paper has gained after a period of time.
Generating Label Cohesive and Well-Formed Adversarial Claims
However, for inference tasks such as fact checking, these triggers often inadvertently invert the meaning of instances they are inserted in.
Transformer Based Multi-Source Domain Adaptation
Here, we investigate the problem of unsupervised multi-source domain adaptation, where a model is trained on labelled data from multiple source domains and must make predictions on a domain for which no labelled data has been seen.
Claim Check-Worthiness Detection as Positive Unlabelled Learning
In applying this, we out-perform the state of the art in two of the three tasks studied for claim check-worthiness detection in English.
NormCo: Deep Disease Normalization for Biomedical Knowledge Base Construction
Biomedical knowledge bases are crucial in modern data-driven biomedical sciences, but auto-mated biomedical knowledge base construction remains challenging.
Rethinking Recurrent Latent Variable Model for Music Composition
Our results suggest that the proposed model has a better statistical resemblance to the musical structure of the training data, which improves the creation of new sequences of music in the style of the originals.
