no code implementations • 19 Feb 2024 • Amelie Wührl, Dustin Wright, Roman Klinger, Isabelle Augenstein
Distorted science communication harms individuals and society as it can lead to unhealthy behavior change and decrease trust in scientific institutions.
no code implementations • 5 Sep 2023 • Dustin Wright, Christian Igel, Gabrielle Samuel, Raghavendra Selvan
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.
no code implementations • 19 Dec 2022 • Dustin Wright, Isabelle Augenstein
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.
no code implementations • 25 Oct 2022 • Andreas Nugaard Holm, Dustin Wright, Isabelle Augenstein
A cheaper alternative is to simply use the softmax based on a single forward pass without dropout to estimate model uncertainty.
no code implementations • 24 Oct 2022 • Dustin Wright, Jiaxin Pei, David Jurgens, Isabelle Augenstein
Whether the media faithfully communicate scientific information has long been a core issue to the science community.
1 code implementation • ACL 2022 • Dustin Wright, David Wadden, Kyle Lo, Bailey Kuehl, Arman Cohan, Isabelle Augenstein, Lucy Lu Wang
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.
1 code implementation • EMNLP 2021 • Dustin Wright, Isabelle Augenstein
Given this, we present a formalization of and study into the problem of exaggeration detection in science communication.
1 code implementation • Findings (ACL) 2021 • Dustin Wright, Isabelle Augenstein
Scientific document understanding is challenging as the data is highly domain specific and diverse.
no code implementations • 10 Dec 2020 • Andreas Nugaard Holm, Barbara Plank, Dustin Wright, Isabelle Augenstein
Citation count prediction is the task of predicting the number of citations a paper has gained after a period of time.
1 code implementation • EMNLP 2020 • Pepa Atanasova, Dustin Wright, Isabelle Augenstein
However, for inference tasks such as fact checking, these triggers often inadvertently invert the meaning of instances they are inserted in.
1 code implementation • EMNLP 2020 • Dustin Wright, Isabelle Augenstein
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.
1 code implementation • Findings of the Association for Computational Linguistics 2020 • Dustin Wright, Isabelle Augenstein
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.
no code implementations • AKBC 2019 • Dustin Wright, Yannis Katsis, Raghav Mehta, Chun-Nan Hsu
Biomedical knowledge bases are crucial in modern data-driven biomedical sciences, but auto-mated biomedical knowledge base construction remains challenging.
no code implementations • 7 Oct 2018 • Eunjeong Stella Koh, Shlomo Dubnov, Dustin Wright
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.