Thumbnails:
List:
Year:
Category:
Session:
Poster:
Getting poster data...
Eric Lu, Michelle Wei, Enrique Noriega, Sateesh Peri, Mihai Surdeanu, Guang Yao (University of Arizona, Tucson, USA)
Over 1 million published biomedical papers are entered into the PubMed database each year, making it practically impossible for researchers to keep up with the rapid literature advances by reading through the published articles. Natural Language Processing (NLP), presents a crucial solution to this problem, enabling rapid extraction of structured information from unstructured text. Here we present VERIT (Visualization of Entity Relationships In Text), an interactive web app for visualizing networks of relationships extracted from scientific literature. VERIT has two main components: 1) a knowledge base of 1.8 million unique biomedical relationships extracted using NLP, and 2) an intuitive web interface that facilitates querying knowledge bases and visualizing results with customizable levels of detail. By facilitating fast information retrieval, connection, and visualization, VERIT represents a step toward automated knowledge synthesis and hypothesis generation from exponentially growing biomedical literature that is impossible to parse manually.