Fact or Fiction: Verifying Scientific Claims

Wadden, David; Lin, Shanchuan; Lo, Kyle; Wang, Lucy Lu; Zuylen, Madeleine van; Cohan, Arman; Hajishirzi, Hannaneh

doi:10.18653/v1/2020.emnlp-main.609

Cited by 165 publications

(211 citation statements)

References 33 publications

Supporting

Mentioning

208

Contrasting

Order By: Relevance

“…One such example is the task of resolving references to concepts across scientific papers and related news articles. This can help scientists understand how their work is being presented to the public by mainstream media or facilitate fact checking of journalists' work (Wadden et al, 2020). A chatbot or recommender that is able to resolve references to current affairs in both news articles and user input could be more effective at suggesting topics that interest the user.…”

Section: Introductionmentioning

confidence: 99%

The feasibility of convalescent plasma therapy in severe COVID- 19 patients: a pilot study

Duan

Liu

et al. 2020

Preprint

130

147

View full text Add to dashboard Cite

Currently, there are no approved specific antiviral agents for 2019 novel coronavirus disease . In this study, ten severe patients confirmed by real-time viral RNA test were enrolled prospectively. One dose of 200 mL convalescent plasma (CP) derived from recently recovered donors with the neutralizing antibody titers above 1:640 was transfused to the patients as an addition to maximal supportive care and antiviral agents. The primary endpoint was the safety of CP transfusion. The second endpoints were the improvement of clinical symptoms and laboratory parameters within 3 days after CP transfusion. The median time from onset of illness to CP transfusion was 16.5 days. After CP transfusion, the level of neutralizing antibody increased rapidly up to 1:640 in five cases, while that of the other four cases maintained at a high level (1:640). The clinical symptoms were significantly improved along with increase of oxyhemoglobin saturation within 3 days. Several parameters tended to improve as compared to pre-transfusion, including increased lymphocyte counts (0.65×10 9 /L vs. 0.76×10 9 /L) and decreased C-reactive protein (55.98 mg/L vs. 18.13 mg/L). Radiological examinations showed varying degrees of absorption of lung lesionswithin 7 days. The viral load was undetectable after transfusion in seven patients who had previous viremia. No severe adverse effects were observed. This study showed CP therapy was welltolerated and could potentially improve the clinical outcomes through neutralizing viremia in severe COVID-19 cases. The optimal dose and time point, as well as the clinical benefit of CP therapy, needs further investigation in larger well-controlled trials. Significance StatementCOVID-19is currently a big threat to global health. However, no specific antiviral agents are available for its treatment. In this work, we explored the feasibility of convalescent plasma (CP) transfusion to rescue severe patients. The results from 10 severe adult cases showed that one dose (200 mL) of CP was welltolerated and could significantly increase or maintain the neutralizing antibodies at a high level, leading to disappearance of viremia in 7 days. Meanwhile, clinical symptoms and paraclinical criteria rapidly improved within 3 days. Radiological examination All rights reserved. No reuse allowed without permission.

show abstract

Section: Introductionmentioning

confidence: 99%

The feasibility of convalescent plasma therapy in severe COVID- 19 patients: a pilot study

Duan

Liu

et al. 2020

Preprint

130

147

View full text Add to dashboard Cite

show abstract

“…Constructing a new dataset that properly frames a new task is a common theme in Deep Learning. Wadden et al [71] construct the SciFact dataset to extend the ideas of FEVER to COVID-19 applications. This is different from classification task formulations previously mentioned in that they are more creative in task design.…”

Section: Misinformation Detectionmentioning

confidence: 99%

“…SciFact and FEVER introduce new datasets that show how supervised learning can tackle Misinformation Detection. Wadden et al [71] design the SciFact dataset to not only classify a claim as true or false, but to provide supporting and refuting evidence as well. Wadden et al [71] deploy a clever annotation scheme of using "citances", sentences in scientific papers that cite another paper, as examples of supporting or refuting evidence for a claim.…”

Section: Misinformation Detectionmentioning

confidence: 99%

Deep Learning applications for COVID-19

2021

View full text Add to dashboard Cite

This survey explores how Deep Learning has battled the COVID-19 pandemic and provides directions for future research on COVID-19. We cover Deep Learning applications in Natural Language Processing, Computer Vision, Life Sciences, and Epidemiology. We describe how each of these applications vary with the availability of big data and how learning tasks are constructed. We begin by evaluating the current state of Deep Learning and conclude with key limitations of Deep Learning for COVID-19 applications. These limitations include Interpretability, Generalization Metrics, Learning from Limited Labeled Data, and Data Privacy. Natural Language Processing applications include mining COVID-19 research for Information Retrieval and Question Answering, as well as Misinformation Detection, and Public Sentiment Analysis. Computer Vision applications cover Medical Image Analysis, Ambient Intelligence, and Vision-based Robotics. Within Life Sciences, our survey looks at how Deep Learning can be applied to Precision Diagnostics, Protein Structure Prediction, and Drug Repurposing. Deep Learning has additionally been utilized in Spread Forecasting for Epidemiology. Our literature review has found many examples of Deep Learning systems to fight COVID-19. We hope that this survey will help accelerate the use of Deep Learning for COVID-19 research.

show abstract

“…For claim verification, a system identifies papers containing evidence that supports or refutes a claim provided in a query. SciFact [ 97 ] ( Row S22 ) is an example of such a system. For clinical diagnostic support, a system aims to assist healthcare providers in clinical practice, e.g.…”

Section: Text Mining Systemsmentioning

confidence: 99%

Text mining approaches for dealing with the rapidly expanding literature on COVID-19

Wang

2020

Briefings in Bioinformatics

Self Cite

View full text Add to dashboard Cite

More than 50 000 papers have been published about COVID-19 since the beginning of 2020 and several hundred new papers continue to be published every day. This incredible rate of scientific productivity leads to information overload, making it difficult for researchers, clinicians and public health officials to keep up with the latest findings. Automated text mining techniques for searching, reading and summarizing papers are helpful for addressing information overload. In this review, we describe the many resources that have been introduced to support text mining applications over the COVID-19 literature; specifically, we discuss the corpora, modeling resources, systems and shared tasks that have been introduced for COVID-19. We compile a list of 39 systems that provide functionality such as search, discovery, visualization and summarization over the COVID-19 literature. For each system, we provide a qualitative description and assessment of the system’s performance, unique data or user interface features and modeling decisions. Many systems focus on search and discovery, though several systems provide novel features, such as the ability to summarize findings over multiple documents or linking between scientific articles and clinical trials. We also describe the public corpora, models and shared tasks that have been introduced to help reduce repeated effort among community members; some of these resources (especially shared tasks) can provide a basis for comparing the performance of different systems. Finally, we summarize promising results and open challenges for text mining the COVID-19 literature.

show abstract

Fact or Fiction: Verifying Scientific Claims

Cited by 165 publications

References 33 publications

The feasibility of convalescent plasma therapy in severe COVID- 19 patients: a pilot study

The feasibility of convalescent plasma therapy in severe COVID- 19 patients: a pilot study

Deep Learning applications for COVID-19

Text mining approaches for dealing with the rapidly expanding literature on COVID-19

Contact Info

Product

Resources

About